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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the start of an event or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the beginning of a new action or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itsch
    -0.80
    ordinary
    -0.61
    warts
    -0.60
    ousing
    -0.59
    ective
    -0.59
    aff
    -0.59
     Britann
    -0.59
    uman
    -0.59
    ilit
    -0.58
    ashi
    -0.58
    POSITIVE LOGITS
     anew
    0.86
     tomorrow
    0.79
     July
    0.77
     TODAY
    0.75
     January
    0.75
     Jan
    0.74
     today
    0.71
    soon
    0.71
    Feb
    0.70
     salaries
    0.70
    Act Density 0.035%

    No Known Activations