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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or entities referenced in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.75
    ICT
    -0.74
    irty
    -0.72
    apter
    -0.72
    ibility
    -0.71
    ittee
    -0.70
    20439
    -0.68
    hesda
    -0.66
    ocument
    -0.66
     Vulkan
    -0.65
    POSITIVE LOGITS
    raq
    0.84
    mith
    0.81
    knit
    0.81
    lad
    0.77
    HAM
    0.77
    rule
    0.77
    ulz
    0.77
    heastern
    0.76
    eller
    0.74
    shore
    0.73
    Act Density 0.029%

    No Known Activations