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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.71
     doubtnut
    -0.69
     interlocutor
    -0.66
     tric
    -0.64
     uter
    -0.64
     Shaksp
    -0.63
     Tuan
    -0.62
     ovale
    -0.62
    }))
    -0.61
     uſed
    -0.61
    POSITIVE LOGITS
    帖最后由
    0.73
     eher
    0.61
     sebaliknya
    0.61
     Instead
    0.60
     instead
    0.60
     inkább
    0.60
     متعلقه
    0.60
    tdessen
    0.59
    それとも
    0.58
     just
    0.57
    Act Density 0.200%

    No Known Activations