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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.73
    interstitial
    -0.68
    orthy
    -0.65
    ACE
    -0.63
    ords
    -0.62
    ãĤ¶
    -0.62
    orses
    -0.61
    olves
    -0.61
    clave
    -0.61
     coverage
    -0.60
    POSITIVE LOGITS
     alas
    1.17
     uh
    0.93
     yeah
    0.90
     interestingly
    0.89
     unsurprisingly
    0.83
     unlike
    0.82
     unfortunately
    0.80
     secondly
    0.80
     yes
    0.78
     needless
    0.75
    Act Density 0.087%

    No Known Activations