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

    Neuronpedia

    INDEX
    Explanations

    present perfect verbs indicating experiences or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Knew
    -0.79
    grew
    -0.78
    wrote
    -0.77
    Took
    -0.74
    took
    -0.73
    became
    -0.71
     engraçadas
    -0.71
    Went
    -0.71
    Gave
    -0.70
     auroit
    -0.69
    POSITIVE LOGITS
     also
    0.71
     indeed
    0.70
     actually
    0.69
     literally
    0.66
     run
    0.63
     consistently
    0.62
     basically
    0.62
     focused
    0.62
     certainly
    0.61
     always
    0.60
    Act Density 0.296%

    No Known Activations