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

    Neuronpedia

    INDEX
    Explanations

    nested structures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otto
    -0.16
    abee
    -0.15
    ottom
    -0.15
    arts
    -0.14
    bias
    -0.14
    kate
    -0.14
    вед
    -0.14
     маÑĢÑĪ
    -0.14
    ÅĻÃŃzenÃŃ
    -0.14
     embarrassment
    -0.14
    POSITIVE LOGITS
    &P
    0.17
    ipa
    0.16
    ius
    0.15
    .Interop
    0.15
    tin
    0.15
    Inlining
    0.15
    endir
    0.14
    astle
    0.14
    &action
    0.14
    /release
    0.14
    Act Density 0.003%

    No Known Activations