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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Ari."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ding
    -0.72
    eners
    -0.66
    enegger
    -0.66
    irk
    -0.65
    limited
    -0.64
    FORMATION
    -0.63
    WARD
    -0.62
    mit
    -0.62
     Fargo
    -0.61
     Confederacy
    -0.60
    POSITIVE LOGITS
    zon
    1.02
    jit
    0.93
    zona
    0.92
    zeb
    0.91
    leans
    0.88
    Ģ
    0.87
    ī
    0.87
    usha
    0.86
    asing
    0.84
    ija
    0.83
    Act Density 0.042%

    No Known Activations