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

    Neuronpedia

    INDEX
    Explanations

    terms related to emotional and physical distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.79
    ,
    -0.60
     to
    -0.54
    :
    -0.51
     is
    -0.47
    .
    -0.46
     trajets
    -0.46
     “
    -0.45
     for
    -0.45
    )
    -0.44
    POSITIVE LOGITS
    OGND
    0.81
     Shakspeare
    0.78
     NDEBUG
    0.77
     Serap
    0.72
     whence
    0.71
     autoradio
    0.71
     clef
    0.71
    PRNewswire
    0.71
     asunder
    0.70
    XtraEditors
    0.69
    Act Density 2.218%

    No Known Activations