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

    Neuronpedia

    INDEX
    Explanations

    uncommon alphanumeric sequences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dynamics
    -0.79
    iant
    -0.74
    olin
    -0.66
     Luther
    -0.66
    zzle
    -0.65
     Bulgar
    -0.64
     outsiders
    -0.64
     Fas
    -0.64
    ados
    -0.63
     underest
    -0.62
    POSITIVE LOGITS
    =~=~
    1.40
    #$
    0.95
    ã
    0.90
    _-
    0.88
    ãģ¦
    0.88
    $
    0.87
    LI
    0.83
    _>
    0.82
    cffffcc
    0.80
    WOR
    0.79
    Act Density 0.013%

    No Known Activations