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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legislation, law enforcement, and socio-political issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     apprehen
    -0.91
     reluct
    -0.81
     disagre
    -0.80
    YMMV
    -0.79
     iirc
    -0.77
     unspeak
    -0.76
     cuck
    -0.76
     horrend
    -0.75
     encomp
    -0.75
     affor
    -0.75
    POSITIVE LOGITS
    keep
    1.09
     keep
    1.06
     Keep
    1.02
    Keep
    0.98
    KEEP
    0.96
     KEEP
    0.96
     kept
    0.95
    kept
    0.92
     keeps
    0.89
     keeping
    0.88
    Act Density 0.078%

    No Known Activations