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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or places ending with specific character sequences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    TY
    -0.70
    wolves
    -0.68
    paren
    -0.67
    pick
    -0.67
     authorization
    -0.65
    mop
    -0.64
    balance
    -0.63
    olation
    -0.63
     honesty
    -0.63
    ty
    -0.61
    POSITIVE LOGITS
    ñ
    1.28
    uthor
    1.19
    ÅŁ
    1.12
    ppa
    1.11
    eva
    1.09
    issance
    1.08
    qt
    1.05
    ð
    1.04
    zza
    1.03
    ÅĤ
    0.98
    Act Density 0.158%

    No Known Activations