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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names with the common substring "kan"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the syllable "kan" and similar phonetic patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ago
    -0.73
    20439
    -0.70
    suit
    -0.68
     Node
    -0.68
    UV
    -0.65
    Grade
    -0.64
    suits
    -0.64
     Promise
    -0.64
     defe
    -0.64
     Latest
    -0.63
    POSITIVE LOGITS
    kered
    0.99
    igans
    0.95
    istani
    0.94
    igan
    0.93
    thus
    0.90
    thal
    0.89
    emonium
    0.86
    ovich
    0.86
    pour
    0.85
    cia
    0.83
    Act Density 0.021%

    No Known Activations