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

    Neuronpedia

    INDEX
    Explanations

    phrases following the pattern "after [event]"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating timing or sequencing of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aez
    -0.86
    cin
    -0.77
    ASE
    -0.70
    NRS
    -0.70
    itect
    -0.69
    olds
    -0.68
    ahime
    -0.68
    geist
    -0.67
    Fa
    -0.67
    baum
    -0.65
    POSITIVE LOGITS
    noon
    0.97
     midnight
    0.94
     supper
    0.83
     sunset
    0.81
     signing
    0.80
     inspecting
    0.80
     lunch
    0.79
     announcing
    0.77
     spotting
    0.76
     completing
    0.75
    Act Density 0.122%

    No Known Activations