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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating justification or rationale

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.55
    Попис
    -0.52
    SequentialGroup
    -0.52
    tagHelperRunner
    -0.47
     reason
    -0.47
    hyrchwyd
    -0.45
     logic
    -0.41
    Jeografia
    -0.40
     للمعارف
    -0.40
     فريبيس
    -0.39
    POSITIVE LOGITS
    帖最后由
    0.40
    vician
    0.38
    RTLI
    0.38
    gaja
    0.37
    setDo
    0.36
     fubject
    0.36
    ⎦
    0.34
    abestanden
    0.34
    火
    0.33
    哋
    0.33
    Act Density 0.005%

    No Known Activations