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

    Neuronpedia

    INDEX
    Explanations

    phrases containing conjunctions, often 'and'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "and" indicating connections or relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ummer
    -0.80
    atan
    -0.74
    utor
    -0.71
    qqa
    -0.69
    anmar
    -0.67
    EMS
    -0.65
    uto
    -0.65
    BAT
    -0.64
    umo
    -0.64
    qu
    -0.63
    POSITIVE LOGITS
     wondered
    1.08
     wished
    0.98
     urge
    0.96
     knew
    0.93
     wants
    0.89
     urges
    0.88
     knows
    0.88
     believes
    0.86
     wanted
    0.85
     wishes
    0.83
    Act Density 0.315%

    No Known Activations