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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific situations or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agin
    -0.80
    thal
    -0.66
    Bas
    -0.63
    ictive
    -0.63
    yan
    -0.63
    Es
    -0.62
    ha
    -0.62
    aches
    -0.62
    gan
    -0.61
    bas
    -0.61
    POSITIVE LOGITS
    soever
    1.23
     asked
    0.82
     confronted
    0.81
    irlf
    0.79
     pressed
    0.78
     they
    0.76
     contacted
    0.72
    */(
    0.71
     she
    0.71
     faced
    0.70
    Act Density 0.124%

    No Known Activations