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

    Neuronpedia

    INDEX
    Explanations

    information related to reports, statistics, and various analysis in written texts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     kindred
    -0.65
    ËĪ
    -0.65
    NetMessage
    -0.64
     dstg
    -0.62
    ':
    -0.61
    uminati
    -0.61
    âĹ¼
    -0.60
     Subtle
    -0.60
    ocracy
    -0.58
     damn
    -0.57
    POSITIVE LOGITS
    sequently
    1.15
    quartered
    1.10
    sequent
    1.04
    cknowled
    0.82
    Additionally
    0.81
     drawback
    0.78
    ogether
    0.78
     however
    0.75
    surprisingly
    0.74
    beit
    0.74
    Act Density 0.712%

    No Known Activations