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

    Neuronpedia

    INDEX
    Explanations

    phrases related to keeping up with information or staying current on a topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a need to stay informed or updated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieri
    -0.81
    ouf
    -0.74
    amiya
    -0.74
    jab
    -0.71
    pecially
    -0.71
    immune
    -0.70
     speaking
    -0.70
    suggest
    -0.69
    jac
    -0.69
    sov
    -0.67
    POSITIVE LOGITS
     regard
    0.88
     dignity
    0.84
     impunity
    0.81
     regards
    0.80
     Dragonbound
    0.78
     us
    0.76
     him
    0.73
     humanity
    0.71
     them
    0.70
     Kitty
    0.67
    Act Density 0.088%

    No Known Activations