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

    Neuronpedia

    INDEX
    Explanations

    references to orangutans

    oai_token-act-pair · gpt-3.5-turbo

    references to orangutans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ×Ļ
    -0.70
    Ö¼
    -0.69
     compensated
    -0.68
    nesday
    -0.68
    ãĥīãĥ©
    -0.68
    ×Ļ×
    -0.67
    ת
    -0.66
    ׾
    -0.66
    ittee
    -0.65
    ×IJ
    -0.65
    POSITIVE LOGITS
    aroo
    1.20
    omez
    1.07
    regate
    0.94
    irl
    0.91
    lasses
    0.90
    ethe
    0.90
    etsu
    0.90
    lia
    0.89
    alore
    0.88
    arin
    0.87
    Act Density 0.026%

    No Known Activations