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

    Neuronpedia

    INDEX
    Explanations

    repeated references to categories or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyen
    -0.15
    elog
    -0.15
    vá
    -0.15
    ãģĤãģ£ãģŁ
    -0.14
    tron
    -0.14
    ãģĤãĤĭ
    -0.14
    Ø©
    -0.14
    those
    -0.14
    ulpt
    -0.13
    äºŃ
    -0.13
    POSITIVE LOGITS
     pes
    0.19
     who
    0.19
    curity
    0.19
    -ci
    0.18
    ched
    0.16
    cales
    0.16
    omba
    0.15
    Pes
    0.15
    umbs
    0.15
     same
    0.15
    Act Density 0.049%

    No Known Activations