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

    Neuronpedia

    INDEX
    Explanations

    references to social justice issues and discussions surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chairs
    -0.75
    Tonight
    -0.70
    [
    -0.65
    thening
    -0.65
    Begin
    -0.64
     Tonight
    -0.63
    orrow
    -0.62
    _____
    -0.61
     guiActiveUnfocused
    -0.61
    rouse
    -0.60
    POSITIVE LOGITS
     Tatt
    0.65
    abwe
    0.64
     Protection
    0.64
     pesky
    0.64
     perennial
    0.63
     obligatory
    0.63
     tremend
    0.62
     another
    0.62
     perenn
    0.62
     Lav
    0.59
    Act Density 0.071%

    No Known Activations