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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or accomplishments happening in succession

    oai_token-act-pair · gpt-3.5-turbo

    instances of consecutive occurrences or repetitions of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onom
    -0.79
    lands
    -0.74
    kin
    -0.73
    adle
    -0.71
    lé
    -0.68
    ocracy
    -0.67
    rol
    -0.67
    hod
    -0.67
    ger
    -0.65
    chen
    -0.65
    POSITIVE LOGITS
     consecutive
    1.17
     consecut
    1.01
     uninterrupted
    0.87
     successive
    0.86
     strugg
    0.84
     sequential
    0.79
     installments
    0.79
     bouts
    0.79
     spaced
    0.79
    omore
    0.75
    Act Density 0.006%

    No Known Activations