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

    Neuronpedia

    INDEX
    Explanations

    Latin characters mixed with special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.94
     ethic
    -0.82
    ajo
    -0.74
     testim
    -0.71
     arrang
    -0.71
     synerg
    -0.70
     circulation
    -0.70
    acles
    -0.69
     srf
    -0.69
    onomy
    -0.69
    POSITIVE LOGITS
    ÃįÃį
    1.08
    Ī
    1.01
    Ĩ
    0.99
    TER
    0.91
    ãĥĺ
    0.90
    ÙĦ
    0.90
    ãĤĭ
    0.89
    ĩ
    0.88
    ĥ
    0.85
    Ãł
    0.84
    Act Density 0.014%

    No Known Activations