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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    actions that imply movement or activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Âł Âł Âł Âł
    -0.73
     Universal
    -0.67
     anten
    -0.66
    ĨĴ
    -0.65
     Ov
    -0.62
     Independence
    -0.62
    ization
    -0.61
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.61
     Imam
    -0.60
     artif
    -0.59
    POSITIVE LOGITS
    ling
    2.14
    led
    2.09
    les
    2.08
    lers
    2.02
    ler
    1.78
    ernaut
    1.55
    lement
    1.53
    lings
    1.53
    lements
    1.44
    le
    1.43
    Act Density 0.081%

    No Known Activations