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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific names with capitalized letters

    oai_token-act-pair · gpt-3.5-turbo

    acronyms and abbreviated terms, particularly those related to titles or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iw
    -0.82
    iol
    -0.81
    iaz
    -0.76
    IK
    -0.75
    igun
    -0.74
    javascript
    -0.73
    CIA
    -0.72
    IO
    -0.71
     Bian
    -0.71
    423
    -0.71
    POSITIVE LOGITS
    st
    0.92
    sts
    0.86
    thirds
    0.85
    geist
    0.83
    ends
    0.80
     Subst
    0.78
    end
    0.78
     subst
    0.78
     Ost
    0.77
    unda
    0.75
    Act Density 0.332%

    No Known Activations