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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names

    oai_token-act-pair · gpt-3.5-turbo

    the letter "l"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aside
    -0.58
     separately
    -0.57
     resultant
    -0.55
     untreated
    -0.54
     subtract
    -0.54
     toss
    -0.54
     compulsory
    -0.54
     compromises
    -0.53
     Paraly
    -0.53
     bare
    -0.53
    POSITIVE LOGITS
    l
    3.63
    lc
    1.98
    ls
    1.95
    lia
    1.84
    lay
    1.81
    lus
    1.77
    lov
    1.77
    los
    1.77
    lio
    1.75
    lik
    1.63
    Act Density 0.031%

    No Known Activations