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

    Neuronpedia

    INDEX
    Explanations

    violent and criminal actions or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nemia
    -0.64
    quarelle
    -0.60
     Zwiebel
    -0.55
    >\<
    -0.53
     Solubility
    -0.53
     Fieber
    -0.53
     etui
    -0.53
    NotImplemented
    -0.52
     meninos
    -0.52
     nè
    -0.51
    POSITIVE LOGITS
    <bos>
    0.76
     apprehen
    0.76
     McLaugh
    0.75
     reconno
    0.73
     gaily
    0.72
     Juf
    0.71
     homeward
    0.69
     Gorb
    0.69
     Bartholo
    0.69
     unspeak
    0.68
    Act Density 0.280%

    No Known Activations