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

    Neuronpedia

    INDEX
    Explanations

    language indicating specificity and detail

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of specifying or detailing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Think
    -0.76
    tumblr
    -0.70
    assic
    -0.68
    imum
    -0.65
    kt
    -0.64
    Throw
    -0.64
    nee
    -0.61
    irt
    -0.60
    bees
    -0.59
    aturated
    -0.59
    POSITIVE LOGITS
     specifics
    1.28
     nor
    0.95
     details
    0.93
     particulars
    0.90
     formally
    0.84
     specific
    0.83
     definitively
    0.82
     exact
    0.81
     anymore
    0.81
     publicly
    0.80
    Act Density 0.226%

    No Known Activations