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

    Neuronpedia

    INDEX
    Explanations

    prepositions and time-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to time and specific timings for actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ants
    -0.73
    tics
    -0.72
    pects
    -0.70
    emen
    -0.69
    lda
    -0.69
    hatt
    -0.68
    isky
    -0.67
    pher
    -0.65
    aston
    -0.64
    ãĤ¹ãĥĪ
    -0.64
    POSITIVE LOGITS
     discretion
    1.46
     predetermined
    1.13
     intervals
    1.09
     concess
    0.99
     least
    0.98
     appropriate
    0.96
     specified
    0.95
    onement
    0.95
     earliest
    0.94
     anytime
    0.92
    Act Density 0.199%

    No Known Activations