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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the passage of time or reference to specific dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fw
    -0.18
    etas
    -0.17
     Barrier
    -0.15
     Reve
    -0.15
     barrier
    -0.14
     Taken
    -0.14
     rem
    -0.13
    adaptive
    -0.13
    çĤİ
    -0.13
    totals
    -0.13
    POSITIVE LOGITS
    istrovstvÃŃ
    0.17
    kova
    0.16
    -haspopup
    0.16
     Bris
    0.15
    ENARIO
    0.15
    637
    0.15
    .dsl
    0.14
     tripod
    0.14
    ché
    0.14
     ãĥĩ
    0.14
    Act Density 0.568%

    No Known Activations