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

    Neuronpedia

    INDEX
    Explanations

    instances of future intentions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IOR
    -0.07
    wa
    -0.06
    enser
    -0.06
    aug
    -0.06
    eing
    -0.06
    anon
    -0.06
    amp
    -0.06
    asha
    -0.05
     circles
    -0.05
    gor
    -0.05
    POSITIVE LOGITS
     Phonetic
    0.07
     оÑĢг
    0.07
    roys
    0.07
    puted
    0.07
    QUIRES
    0.07
    ingroup
    0.07
    agged
    0.07
    ardless
    0.07
    prite
    0.06
    keley
    0.06
    Act Density 0.008%

    No Known Activations