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

    Neuronpedia

    INDEX
    Explanations

    questions and reasons related to choices or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    posable
    -0.17
    åIJ¦
    -0.15
    posal
    -0.14
    qed
    -0.14
    preload
    -0.14
    pur
    -0.14
    åĪĢ
    -0.14
    ilater
    -0.13
    jian
    -0.13
    ãĥ¥
    -0.13
    POSITIVE LOGITS
    iaux
    0.20
     Blasio
    0.15
    aker
    0.14
     FetchType
    0.14
    /fonts
    0.14
    ìłĢ
    0.14
    oks
    0.14
    ourt
    0.14
    aria
    0.14
    verity
    0.14
    Act Density 0.137%

    No Known Activations