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

    Neuronpedia

    INDEX
    Explanations

    affirmative or certain statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nick
    -0.16
    anca
    -0.15
    agan
    -0.14
    ạt
    -0.14
    atego
    -0.14
    ocking
    -0.14
    leta
    -0.14
     sana
    -0.14
    ãģĤãģĤ
    -0.14
    anim
    -0.13
    POSITIVE LOGITS
    ech
    0.17
    otte
    0.15
    ume
    0.15
     fewer
    0.14
    FD
    0.14
    forth
    0.14
    014
    0.14
    296
    0.14
    ignum
    0.14
    ificates
    0.14
    Act Density 0.017%

    No Known Activations