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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their implications in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighton
    -0.15
    okrat
    -0.15
    obot
    -0.14
    isas
    -0.14
    Viol
    -0.14
     plá
    -0.14
    atty
    -0.13
    oleÄį
    -0.13
    AL
    -0.13
     Viol
    -0.13
    POSITIVE LOGITS
     doz
    0.17
    inters
    0.15
     Primitive
    0.15
    itori
    0.15
    angs
    0.15
    jom
    0.14
    edis
    0.14
    plitude
    0.14
    unei
    0.14
    anmar
    0.13
    Act Density 0.004%

    No Known Activations