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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific individuals, possibly in positions of power or influence

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to the concept of "conditions"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kaya
    -0.77
    dfx
    -0.73
    cca
    -0.70
    ku
    -0.67
    ching
    -0.67
    ngth
    -0.66
    yrim
    -0.66
    doms
    -0.65
    DW
    -0.65
    chens
    -0.64
    POSITIVE LOGITS
    ensed
    0.94
    itionally
    0.92
    itional
    0.92
    uctor
    0.91
    uit
    0.85
    itions
    0.84
    ega
    0.82
    uits
    0.80
    iments
    0.76
    uitous
    0.76
    Act Density 0.028%

    No Known Activations