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

    Neuronpedia

    INDEX
    Explanations

    references to potential outcomes or considerations related to decision-making

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

    Contractions and possessives

    np_acts-logits-general · gemini-2.0-flash

    archaic and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.80
    Vegeu
    -0.50
     ab
    -0.45
     phần
    -0.43
     kans
    -0.41
     Y
    -0.41
    footed
    -0.40
     Takt
    -0.40
    jami
    -0.39
    setting
    -0.39
    POSITIVE LOGITS
    tanleria
    0.97
     myſelf
    0.90
     Jefus
    0.83
     itſelf
    0.83
     ddelweddau
    0.79
    ंदीखरीदारी
    0.78
     Monfieur
    0.77
     Мексичка
    0.76
     Majefty
    0.76
    intios
    0.75
    Act Density 0.030%

    No Known Activations