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

    Neuronpedia

    INDEX
    Explanations

    casual conversational phrases and expressions of personal opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑĤи
    -0.15
     azal
    -0.14
    DMIN
    -0.14
    (æĹ¥
    -0.14
     æ¡
    -0.13
    nty
    -0.13
    à¹ĥ
    -0.13
    Disappear
    -0.13
    .Promise
    -0.13
    اÙĤع
    -0.13
    POSITIVE LOGITS
    opus
    0.16
    ť
    0.16
    fed
    0.15
    apus
    0.14
    eil
    0.14
    fds
    0.14
    illard
    0.14
    690
    0.14
    ruk
    0.14
    ayo
    0.13
    Act Density 0.523%

    No Known Activations