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

    Neuronpedia

    INDEX
    Explanations

    words related to emphasizing or repeating information

    oai_token-act-pair · gpt-3.5-turbo

    instances of emphasizing, reiterating, and corroborating information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grail
    -0.68
    RAW
    -0.64
    farm
    -0.64
     pecul
    -0.63
    AFTA
    -0.63
     Typhoon
    -0.63
     Eye
    -0.62
    soever
    -0.62
     Surv
    -0.59
     blindly
    -0.59
    POSITIVE LOGITS
    uating
    1.37
    uation
    1.31
    uated
    1.28
    ating
    1.25
    uations
    1.24
    idated
    1.23
    ation
    1.19
    ued
    1.17
    uates
    1.16
    uing
    1.15
    Act Density 0.085%

    No Known Activations