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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax elements and related commands

    oai_token-act-pair · gpt-3.5-turbo

    the presence of technical or coding terms and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otos
    -0.62
    ÃĥÃĤ
    -0.57
     tradem
    -0.55
     Pwr
    -0.55
     eleph
    -0.55
     incarn
    -0.55
    ÃĥÃĤÃĥÃĤ
    -0.53
     glim
    -0.53
    isations
    -0.52
     drift
    -0.51
    POSITIVE LOGITS
     [
    2.64
    [
    2.26
    [/
    2.23
     [/
    2.19
     ["
    1.99
     [-
    1.99
     [*
    1.75
     ['
    1.73
     [(
    1.72
     [+
    1.68
    Act Density 0.339%

    No Known Activations