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

    Neuronpedia

    INDEX
    Explanations

    words related to errors or imperfections

    oai_token-act-pair · gpt-3.5-turbo

    terms related to flaws, weaknesses, and deficiencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rollers
    -0.86
    amaz
    -0.74
    Ń·
    -0.73
    iversary
    -0.70
     Carbuncle
    -0.68
    da
    -0.68
    cow
    -0.66
    upt
    -0.65
    rontal
    -0.64
    ctors
    -0.63
    POSITIVE LOGITS
     weaknesses
    1.08
     flaws
    1.07
     inherent
    1.03
     flaw
    0.99
     plag
    0.96
     vulnerabilities
    0.91
     weakness
    0.84
     loopholes
    0.84
     vulner
    0.79
     deficiencies
    0.78
    Act Density 0.085%

    No Known Activations