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

    Neuronpedia

    INDEX
    Explanations

    key phrases related to personal experiences and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     próximo
    -0.16
    Late
    -0.15
    andal
    -0.14
    late
    -0.14
     afterward
    -0.14
    astes
    -0.13
     Late
    -0.13
    AREST
    -0.13
    byn
    -0.13
     tarde
    -0.13
    POSITIVE LOGITS
     previously
    0.77
     Previously
    0.60
    Previously
    0.59
     previous
    0.46
     earlier
    0.44
     formerly
    0.44
     originally
    0.43
    formerly
    0.39
     prev
    0.36
    viously
    0.36
    Act Density 0.186%

    No Known Activations