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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express intentions, objectives, or purposes behind actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aples
    -0.72
    heed
    -0.70
    uba
    -0.70
    rete
    -0.69
    avorite
    -0.68
    cit
    -0.66
    vez
    -0.62
    orthodox
    -0.60
    asca
    -0.60
    zek
    -0.59
    POSITIVE LOGITS
     caveat
    0.83
     assumption
    0.80
    same
    0.69
     premise
    0.66
    liest
    0.66
     of
    0.64
    ultimate
    0.62
     refrain
    0.62
     à¨
    0.59
    onym
    0.59
    Act Density 0.164%

    No Known Activations