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

    Neuronpedia

    INDEX
    Explanations

    proper names "Ari" and variations of the name

    oai_token-act-pair · gpt-3.5-turbo

    the name "Ari" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eners
    -0.75
    é¾įå¥ij士
    -0.74
    ding
    -0.71
    WARD
    -0.69
    enegger
    -0.69
    limited
    -0.68
    é¾
    -0.64
     Newfoundland
    -0.62
     Accountability
    -0.61
    itionally
    -0.60
    POSITIVE LOGITS
    zon
    0.97
    zona
    0.95
    ī
    0.90
    zeb
    0.90
    leans
    0.86
    jit
    0.86
    agraph
    0.83
    usha
    0.82
    asing
    0.82
    Ģ
    0.81
    Act Density 0.024%

    No Known Activations