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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "re-" indicating repetition or return actions

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

    followed by an action or statement

    np_acts-logits-general · gemini-2.0-flash

    indicates or suggests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.77
     GenerationType
    -0.63
     contextLoads
    -0.63
    AsUp
    -0.61
    principalTable
    -0.60
    XmlAccessType
    -0.60
     AssemblyCompany
    -0.60
    ProcessEvent
    -0.59
    drawSprites
    -0.59
    featureID
    -0.58
    POSITIVE LOGITS
     implies
    0.86
     implied
    0.84
     imply
    0.77
     mention
    0.73
     implying
    0.72
     clearly
    0.67
    imply
    0.67
     mentions
    0.66
     reference
    0.64
     statement
    0.64
    Act Density 0.430%

    No Known Activations