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

    Neuronpedia

    INDEX
    Explanations

    words related to judgment or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditions or settings for actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ependence
    -0.72
    formance
    -0.71
    ulla
    -0.66
    annels
    -0.64
    idious
    -0.63
    ciplinary
    -0.61
    aida
    -0.61
     candidacy
    -0.61
    20439
    -0.61
     rapport
    -0.58
    POSITIVE LOGITS
     dunno
    1.00
     Hmm
    0.91
    yeah
    0.87
    hhh
    0.87
    Okay
    0.86
    mmm
    0.86
    Sounds
    0.85
     admittedly
    0.84
     Sounds
    0.83
     guessed
    0.82
    Act Density 1.038%

    No Known Activations