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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the suffix "st" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thumbs
    -0.66
     disabling
    -0.66
     deaf
    -0.62
     amy
    -0.60
     timely
    -0.59
     calming
    -0.58
     Haram
    -0.58
     Bills
    -0.55
     Peel
    -0.55
     crest
    -0.55
    POSITIVE LOGITS
    oppers
    1.19
    retch
    1.17
    oppable
    1.16
    itute
    1.14
    itution
    1.13
    hetics
    1.10
    ructure
    1.08
    alk
    1.07
    rikes
    1.07
    rict
    1.06
    Act Density 0.041%

    No Known Activations