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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the timing or occurrence of events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "come" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ricular
    -0.63
    ochond
    -0.62
    itcher
    -0.60
    ingham
    -0.60
    eering
    -0.58
    berries
    -0.58
    roots
    -0.57
    bows
    -0.56
    nie
    -0.56
    è¦ļéĨĴ
    -0.55
    POSITIVE LOGITS
     amid
    1.14
     amidst
    1.03
     weeks
    0.87
     months
    0.80
     despite
    0.76
     shortly
    0.74
    Days
    0.73
     days
    0.73
    lehem
    0.73
    withstanding
    0.72
    Act Density 0.048%

    No Known Activations