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

    Neuronpedia

    INDEX
    Explanations

    words related to combining, merging, or aligning different entities or ideas

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to collaboration and merging ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grim
    -0.73
    ij士
    -0.70
    ·
    -0.65
    ISTER
    -0.65
    keeper
    -0.65
    taker
    -0.64
    DER
    -0.64
    OSP
    -0.63
    OUT
    -0.63
    FontSize
    -0.62
    POSITIVE LOGITS
     sexes
    1.08
     dots
    1.04
     seamlessly
    1.01
     between
    0.98
     Between
    0.92
    between
    0.91
     disparate
    0.88
     twins
    0.82
     pairs
    0.82
     genders
    0.80
    Act Density 0.222%

    No Known Activations