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

    Neuronpedia

    INDEX
    Explanations

    words related to temporal sequences or events

    oai_token-act-pair · gpt-3.5-turbo

    the word "when" indicating temporal references or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agin
    -0.69
    kaya
    -0.66
    harm
    -0.66
    åĤ
    -0.64
    edly
    -0.61
    alian
    -0.60
    aking
    -0.60
    SPONSORED
    -0.60
    atic
    -0.59
    PHOTOS
    -0.59
    POSITIVE LOGITS
    soever
    1.38
     asked
    0.89
     confronted
    0.87
     pressed
    0.80
    irlf
    0.79
     faced
    0.76
     contacted
    0.72
    quickShipAvailable
    0.72
    phies
    0.70
    IPS
    0.69
    Act Density 0.087%

    No Known Activations