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

    Neuronpedia

    INDEX
    Explanations

    discussions about dilemmas and moral choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comparisons and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fhew
    -0.48
     quæ
    -0.40
     himſelf
    -0.39
    stdc
    -0.38
    wiſe
    -0.35
     leſs
    -0.35
     tranſ
    -0.34
    よいよ
    -0.34
     raiſ
    -0.34
     purpoſe
    -0.33
    POSITIVE LOGITS
    httphttps
    0.57
    tanleria
    0.57
    SpringRunner
    0.56
    oneofs
    0.52
    لينكات
    0.49
     виправивши
    0.49
     oprot
    0.48
    Дереккөздер
    0.48
     ninguno
    0.48
    fromnode
    0.48
    Act Density 0.160%

    No Known Activations