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

    Neuronpedia

    INDEX
    Explanations

    instances of events happening at specific locations and times

    oai_token-act-pair · gpt-3.5-turbo

    the word "when" repeatedly signaling temporal context in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agin
    -0.73
    ictive
    -0.73
    aches
    -0.65
    thal
    -0.65
    aido
    -0.64
    harm
    -0.63
    opt
    -0.63
    rolet
    -0.63
    bear
    -0.62
    email
    -0.61
    POSITIVE LOGITS
    soever
    1.15
    */(
    0.78
    irlf
    0.77
     confronted
    0.76
     pressed
    0.75
     asked
    0.74
    wcsstore
    0.70
    EStream
    0.70
     they
    0.70
     faced
    0.68
    Act Density 0.122%

    No Known Activations