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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or opposition

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitional phrases indicating contrast or continuation in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irie
    -0.76
    catentry
    -0.72
    iquette
    -0.70
    gang
    -0.68
    cel
    -0.68
    idy
    -0.66
    igham
    -0.66
    anium
    -0.65
    estine
    -0.64
    ħĭ
    -0.64
    POSITIVE LOGITS
     namely
    1.34
     though
    0.96
     however
    0.96
     considering
    0.91
     albeit
    0.89
     eh
    0.88
     because
    0.88
     judging
    0.86
     according
    0.86
     wherein
    0.85
    Act Density 0.320%

    No Known Activations