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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or terms related to exclusions and limitations

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

    not or no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OMITTED
    -0.34
    ępo
    -0.34
     Specific
    -0.33
     号
    -0.32
    uré
    -0.32
    号
    -0.32
    een
    -0.32
    EE
    -0.31
     Time
    -0.31
    曖昧さ回避
    -0.31
    POSITIVE LOGITS
    0.67
    IsMutable
    0.54
    SharedCtor
    0.52
    principalColumn
    0.51
    Werdegang
    0.49
    EndProject
    0.49
     transfieras
    0.49
    OGND
    0.49
     فريبيس
    0.48
     avoient
    0.47
    Act Density 0.092%

    No Known Activations