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

    Neuronpedia

    INDEX
    Explanations

    names or words with 'll' in them

    oai_token-act-pair · gpt-3.5-turbo

    recurring instances of a specific syllable or phonetic pattern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [_
    -0.62
     "{
    -0.59
    hered
    -0.57
     conformity
    -0.57
    Chan
    -0.56
    lished
    -0.55
     effected
    -0.55
    ··
    -0.54
    в
    -0.54
    ãĤ§
    -0.54
    POSITIVE LOGITS
    ibrary
    1.19
    oyd
    1.18
    uminati
    1.18
    ounge
    1.12
    sburgh
    1.03
    owship
    1.02
    ipop
    1.01
    ateral
    0.99
    ength
    0.98
    iard
    0.98
    Act Density 0.038%

    No Known Activations