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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets starting with special characters

    oai_token-act-pair · gpt-3.5-turbo

    segments related to programming or technical code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciplinary
    -0.59
    atform
    -0.59
     informed
    -0.53
    autions
    -0.53
     Elections
    -0.52
    tsky
    -0.52
     fanbase
    -0.51
    Politics
    -0.51
     political
    -0.51
     impeachment
    -0.51
    POSITIVE LOGITS
     etc
    1.10
    etc
    0.82
     respectively
    0.74
     Lastly
    0.72
     likewise
    0.59
     prest
    0.55
     Fib
    0.55
     SetFontSize
    0.54
    whatever
    0.53
    another
    0.53
    Act Density 0.525%

    No Known Activations