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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of closing or silencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heet
    -0.17
    gent
    -0.16
    heets
    -0.16
    862
    -0.16
    ont
    -0.16
    iced
    -0.15
    /=
    -0.15
    hoot
    -0.15
    aggio
    -0.14
    idis
    -0.14
    POSITIVE LOGITS
    ters
    0.40
     shut
    0.28
    ting
    0.28
    tings
    0.25
     down
    0.24
    TING
    0.24
    -down
    0.22
    tdown
    0.22
    TERS
    0.21
     shuts
    0.20
    Act Density 0.008%

    No Known Activations