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

    Neuronpedia

    INDEX
    Explanations

    words related to comparisons, contrast, and alternatives

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating occurrences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abul
    -0.76
     Scrolls
    -0.73
    Pen
    -0.68
    ESE
    -0.68
     Addiction
    -0.68
    rb
    -0.64
    atal
    -0.64
    ich
    -0.64
    Nav
    -0.64
    fell
    -0.64
    POSITIVE LOGITS
     finally
    1.24
     ultimately
    1.12
     then
    1.05
    etc
    1.04
     etc
    1.03
     downright
    1.01
     generally
    0.95
     frankly
    0.91
     vo
    0.90
     basically
    0.89
    Act Density 0.196%

    No Known Activations