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

    Neuronpedia

    INDEX
    Explanations

    references to individuals named "Dan."

    oai_token-act-pair · gpt-3.5-turbo

    the token used to denote end-of-text in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llor
    -0.72
     extremes
    -0.66
    CLASSIFIED
    -0.63
     membr
    -0.62
     margins
    -0.62
    Reloaded
    -0.61
    */(
    -0.61
     conspicuous
    -0.61
     imperson
    -0.61
     unaccount
    -0.60
    POSITIVE LOGITS
    zig
    1.37
    forth
    1.35
    ilo
    1.11
    coni
    1.04
    ube
    1.02
    wei
    1.02
    ica
    0.96
    alog
    0.95
     Rather
    0.92
    iken
    0.92
    Act Density 0.017%

    No Known Activations