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

    Neuronpedia

    INDEX
    Explanations

    words related to immediate actions or time-sensitive events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word 'immediately' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    smanship
    -0.79
    midt
    -0.70
    mic
    -0.68
    glers
    -0.66
    chance
    -0.66
    MIC
    -0.64
    mere
    -0.64
    CHQ
    -0.64
    gerald
    -0.61
    sever
    -0.61
    POSITIVE LOGITS
     thereafter
    1.01
    aneously
    0.97
     recognizable
    0.96
     regretted
    0.88
     afterward
    0.86
     recogn
    0.86
     identifiable
    0.85
     upon
    0.84
     afterwards
    0.83
     gratification
    0.76
    Act Density 0.037%

    No Known Activations