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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.76
     validamos
    -0.74
    AndEndTag
    -0.71
    createCanvas
    -0.70
    saraba
    -0.67
    SEGUIR
    -0.65
     textStatus
    -0.65
    المناصب
    -0.64
     Meksiku
    -0.63
    Gambas
    -0.62
    POSITIVE LOGITS
    I
    0.63
     I
    0.60
    i
    0.51
    @
    0.49
    ma
    0.48
    aire
    0.47
    engers
    0.46
     Terrible
    0.45
    this
    0.45
     oni
    0.45
    Act Density 0.425%

    No Known Activations