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

    Neuronpedia

    INDEX
    Explanations

    terms related to significant negative outcomes or critiques

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.53
    itzender
    -0.50
    honest
    -0.47
    Hentet
    -0.47
    expandindo
    -0.47
     Wege
    -0.46
    цепт
    -0.46
    الإنجليزية
    -0.45
     jogos
    -0.45
    defineProperty
    -0.45
    POSITIVE LOGITS
     تضيفلها
    0.91
     فريبيس
    0.69
     pleaſure
    0.69
    ์ตูน
    0.64
    ----</
    0.64
     itſelf
    0.64
     SwitchCompat
    0.64
     pstmt
    0.63
     ordeal
    0.63
     sinner
    0.62
    Act Density 0.164%

    No Known Activations