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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal matters or criminal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.96
     caucuses
    -0.70
    CBC
    -0.62
    ħĭ
    -0.60
     loyalty
    -0.59
     deaf
    -0.59
     exception
    -0.58
     mean
    -0.58
     inconsistency
    -0.57
    ¿½
    -0.57
    POSITIVE LOGITS
    agall
    0.95
    andise
    0.90
    ierrez
    0.82
    anamo
    0.82
    ultural
    0.80
    intestinal
    0.76
    ulture
    0.75
    raltar
    0.74
    ppe
    0.74
    amic
    0.73
    Act Density 2.631%

    No Known Activations