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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    recurring punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AGE
    -0.74
    minster
    -0.69
    owed
    -0.67
    Bind
    -0.65
    Pont
    -0.64
    scribe
    -0.63
    liest
    -0.63
    owe
    -0.62
    oodle
    -0.62
    IBLE
    -0.61
    POSITIVE LOGITS
     although
    1.08
     insofar
    1.04
     unlike
    1.01
     according
    0.94
     despite
    0.92
     there
    0.91
     lest
    0.87
     whereas
    0.84
     while
    0.83
     whenever
    0.83
    Act Density 0.164%

    No Known Activations