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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific numerical values

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the word "at" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lens
    -0.77
    vous
    -0.76
    FTWARE
    -0.75
    PLA
    -0.71
    Russ
    -0.71
    birds
    -0.70
    Winged
    -0.66
    fill
    -0.66
    clip
    -0.64
    lish
    -0.64
    POSITIVE LOGITS
     least
    1.23
    abase
    1.08
    onement
    0.98
    rial
    0.89
    roph
    0.84
    oned
    0.83
     dusk
    0.82
     intervals
    0.81
    rophic
    0.80
    omic
    0.80
    Act Density 0.191%

    No Known Activations