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

    Neuronpedia

    INDEX
    Explanations

    instances of a time-related event or action happening repeatedly over a period of time

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating ongoing actions or historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sins
    -0.73
    beer
    -0.68
     desk
    -0.65
     sins
    -0.62
    sin
    -0.62
    edi
    -0.61
     Others
    -0.58
     desks
    -0.58
    eus
    -0.58
    ovo
    -0.57
    POSITIVE LOGITS
     steadily
    0.82
     continuously
    0.77
     progressively
    0.76
     countless
    0.73
     consistently
    0.70
     racked
    0.67
    anco
    0.67
    continue
    0.66
     WATCHED
    0.66
     sporadic
    0.66
    Act Density 0.354%

    No Known Activations