Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to following instructions or guidelines from manufacturers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following directions or instructions

    np_acts-logits-general · gemini-2.0-flash

    follow manufacturer instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.44
    IsMutable
    -0.42
    offsetof
    -0.39
     prote
    -0.39
    WithMany
    -0.38
    ThroughAttribute
    -0.36
    writeFieldEnd
    -0.35
    HostException
    -0.35
    astify
    -0.34
     Exactos
    -0.34
    POSITIVE LOGITS
     instructions
    1.98
    instructions
    1.73
     Instructions
    1.69
    Instructions
    1.61
     INSTRUCTIONS
    1.55
     instruction
    1.46
     instrucciones
    1.46
     directions
    1.38
    INSTRUCTIONS
    1.35
    instruction
    1.34
    Act Density 0.359%

    No Known Activations