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

    Neuronpedia

    INDEX
    Explanations

    specific news outlets

    oai_token-act-pair · gpt-3.5-turbo

    references to news publications and alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierre
    -0.80
    amiya
    -0.78
    ersen
    -0.76
    igham
    -0.73
    ħĭ
    -0.71
    Äĩ
    -0.69
     Oss
    -0.64
    utical
    -0.64
    Gy
    -0.63
    */(
    -0.63
    POSITIVE LOGITS
     Mubarak
    0.69
    zai
    0.69
    clinton
    0.68
     eleph
    0.65
    umbn
    0.64
     Newsp
    0.62
    anamo
    0.62
    Donnell
    0.62
     Leopard
    0.61
     NCT
    0.61
    Act Density 0.156%

    No Known Activations