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

    Neuronpedia

    INDEX
    Explanations

    computer programming-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and topics related to technology and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )."
    -0.79
    ¶ħ
    -0.73
     Deng
    -0.71
    )",
    -0.71
    Sov
    -0.69
    Eva
    -0.69
    uced
    -0.68
    Tes
    -0.67
     Kab
    -0.65
     Ic
    -0.65
    POSITIVE LOGITS
     consists
    0.82
     consist
    0.72
    EMBER
    0.72
     refers
    0.68
     consisted
    0.68
    ETHOD
    0.67
    ajor
    0.67
     Major
    0.65
     aka
    0.63
     evaluates
    0.62
    Act Density 0.466%

    No Known Activations