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

    Neuronpedia

    INDEX
    Explanations

    sentences that express personal beliefs or emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trÆ°á»Łng
    -0.16
    wap
    -0.16
    earer
    -0.15
     Hope
    -0.15
    canf
    -0.15
    witter
    -0.15
    .Suppress
    -0.14
    _flutter
    -0.14
    .forRoot
    -0.14
    odate
    -0.14
    POSITIVE LOGITS
     abst
    0.16
    aser
    0.15
    itar
    0.15
    489
    0.15
    alone
    0.15
     Sanders
    0.15
    ivan
    0.15
    reserved
    0.15
    代
    0.15
    uted
    0.14
    Act Density 0.255%

    No Known Activations