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

    Neuronpedia

    INDEX
    Explanations

    the word "much" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.80
    saf
    -0.75
    ħĭ
    -0.74
    Ń·
    -0.66
    swer
    -0.64
    emies
    -0.64
    ²¾
    -0.63
    pta
    -0.62
    iversary
    -0.61
    othy
    -0.60
    POSITIVE LOGITS
     emphasis
    0.72
    bang
    0.68
    assi
    0.66
    oooo
    0.66
    ymm
    0.63
     attention
    0.62
     hoop
    0.60
     firepower
    0.59
     dmg
    0.59
     damage
    0.59
    Act Density 0.015%

    No Known Activations