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

    Neuronpedia

    INDEX
    Explanations

    dialogues and reported speech in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucu
    -0.17
    erv
    -0.16
    atts
    -0.15
    .openConnection
    -0.15
    ervo
    -0.14
    geb
    -0.14
    ÃŃrk
    -0.14
    arseille
    -0.13
    fty
    -0.13
    ToWorld
    -0.13
    POSITIVE LOGITS
    aepernick
    0.15
    lü
    0.14
    NAS
    0.14
     noses
    0.13
    Purpose
    0.13
     quant
    0.13
    ÙĤاÙħ
    0.13
    -san
    0.13
    undef
    0.13
     Zucker
    0.13
    Act Density 0.060%

    No Known Activations