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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions or uncertainties

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agin
    -0.75
    gan
    -0.71
    rolet
    -0.66
    gur
    -0.66
    zzi
    -0.65
    idan
    -0.64
    athom
    -0.61
    yre
    -0.60
    aine
    -0.60
    yi
    -0.60
    POSITIVE LOGITS
    soever
    1.36
    irlf
    0.96
     confronted
    0.81
    abouts
    0.77
     faced
    0.76
     pressed
    0.71
     comparing
    0.71
     asked
    0.68
    theless
    0.68
    IPS
    0.66
    Act Density 0.133%

    No Known Activations