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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols used in different languages or encoding formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.81
     Hitchcock
    -0.81
     horizont
    -0.79
    wagen
    -0.69
    espie
    -0.69
    enegger
    -0.67
     agre
    -0.65
    sburgh
    -0.64
    itude
    -0.64
     shots
    -0.63
    POSITIVE LOGITS
    ²¾
    1.47
    ¾
    1.42
    ´
    1.41
    ŃĶ
    1.33
    ł
    1.33
    ģ«
    1.32
    Ł
    1.30
    ©¶æ¥µ
    1.27
    ¹
    1.27
    §
    1.27
    Act Density 0.002%

    No Known Activations