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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or contractual terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "disparagement" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.81
    ¥µ
    -0.73
    andestine
    -0.71
    Accessory
    -0.68
    ELD
    -0.67
    aina
    -0.67
    uge
    -0.65
    ä½ľ
    -0.65
     customary
    -0.64
    urst
    -0.64
    POSITIVE LOGITS
    allel
    1.17
    liament
    0.97
    imony
    0.93
    anoia
    0.88
    ison
    0.82
    vati
    0.80
    ities
    0.80
    amount
    0.79
    ion
    0.78
    ietal
    0.76
    Act Density 0.007%

    No Known Activations