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

    Neuronpedia

    INDEX
    Explanations

    words related to confirmation or verification

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "confirmation."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.79
    @#&
    -0.75
    ð
    -0.73
    hner
    -0.70
    Lua
    -0.68
    enium
    -0.68
    bler
    -0.68
    DragonMagazine
    -0.68
    gom
    -0.67
    Wan
    -0.67
    POSITIVE LOGITS
    irmation
    1.20
    atory
    1.06
    ance
    0.89
    irming
    0.83
     confirmation
    0.82
    antes
    0.80
    irms
    0.79
    essions
    0.77
    ations
    0.76
    ities
    0.76
    Act Density 0.027%

    No Known Activations