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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating potential outcomes or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cke
    -0.21
    shima
    -0.17
    lod
    -0.16
    pei
    -0.15
    öst
    -0.15
    aleza
    -0.14
    inded
    -0.14
    gor
    -0.14
    ingleton
    -0.14
    ittest
    -0.14
    POSITIVE LOGITS
     potentially
    0.18
    ErrorException
    0.17
    814
    0.15
    ormap
    0.15
     tomorrow
    0.15
     easily
    0.14
    orses
    0.14
    jit
    0.14
    翼
    0.14
    ç¹ģ
    0.14
    Act Density 0.084%

    No Known Activations