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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "not only" is used

    oai_token-act-pair · gpt-3.5-turbo

    instances of phrases that denote comparisons or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cko
    -0.75
    onement
    -0.67
    cel
    -0.63
    ply
    -0.62
    wash
    -0.62
    hack
    -0.61
    èĢħ
    -0.60
    irect
    -0.60
    qus
    -0.60
    eker
    -0.59
    POSITIVE LOGITS
     nor
    0.98
     secondly
    0.97
     moreover
    0.93
     but
    0.87
     albeit
    0.74
     insofar
    0.74
     though
    0.74
    Secondly
    0.72
    }"
    0.72
     namely
    0.72
    Act Density 0.136%

    No Known Activations