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

    Neuronpedia

    INDEX
    Explanations

    technical terms and product descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to technological products or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.80
    PLA
    -0.62
    .")
    -0.60
     ."
    -0.59
    .).
    -0.57
    )."
    -0.57
     .)
    -0.54
    interrupted
    -0.53
    think
    -0.52
     ).
    -0.52
    POSITIVE LOGITS
     Profile
    0.79
    ':
    0.73
     âĵĺ
    0.69
    odore
    0.68
    \":
    0.64
     00000000
    0.60
    ":{"
    0.58
     Sets
    0.57
     /
    0.57
     Variant
    0.57
    Act Density 0.845%

    No Known Activations