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

    Neuronpedia

    INDEX
    Explanations

    grammatical structures and phrases indicating formal titles and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cork
    -0.17
    .styleable
    -0.16
     Cove
    -0.15
     Cousins
    -0.15
     Crescent
    -0.15
    каÑĤ
    -0.15
    /Card
    -0.14
     addCriterion
    -0.14
    cott
    -0.14
    /card
    -0.14
    POSITIVE LOGITS
    -ch
    0.77
    -Ch
    0.69
    CH
    0.68
    ch
    0.65
     CH
    0.63
    Ch
    0.61
    _ch
    0.60
    .ch
    0.57
    _Ch
    0.56
    chi
    0.54
    Act Density 0.473%

    No Known Activations