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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a duration of time

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the duration of time perceived as excessive or unacceptable

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gall
    -0.58
     equivalents
    -0.55
    ãĥ¥
    -0.54
    emet
    -0.54
    oké
    -0.54
    anguage
    -0.53
    oat
    -0.52
     defaults
    -0.51
     counterparts
    -0.51
    -0.51
    POSITIVE LOGITS
     long
    1.84
     LONG
    1.59
    long
    1.42
    Long
    1.25
     longest
    1.23
     longer
    1.19
     awhile
    1.16
     short
    1.11
    short
    1.06
     Long
    1.03
    Act Density 0.090%

    No Known Activations