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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs and phrases indicating completion of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancellor
    -0.16
    ábado
    -0.15
    å»Ĭ
    -0.15
    bÃŃr
    -0.15
    istrovstvÃŃ
    -0.14
    åij
    -0.14
    ilde
    -0.13
    chner
    -0.13
    atrix
    -0.13
     Fly
    -0.13
    POSITIVE LOGITS
     Bilim
    0.15
    важа
    0.14
    acao
    0.14
    uto
    0.14
    eo
    0.14
    zer
    0.13
    豪
    0.13
    roof
    0.13
    Ïģγ
    0.13
     Gran
    0.13
    Act Density 0.115%

    No Known Activations