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

    Neuronpedia

    INDEX
    Explanations

    key phrases associated with actions and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alic
    -0.17
    agina
    -0.16
     licked
    -0.15
    .scalablytyped
    -0.14
    lines
    -0.14
    ILLA
    -0.14
    lij
    -0.14
     Royale
    -0.14
    bak
    -0.14
    779
    -0.13
    POSITIVE LOGITS
     Kendall
    0.16
    ools
    0.16
    /misc
    0.15
    vi
    0.15
    umph
    0.15
    -d
    0.15
     Dare
    0.15
     Dong
    0.14
    -D
    0.14
    oni
    0.14
    Act Density 0.033%

    No Known Activations