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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "shut" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idis
    -0.17
    /=
    -0.15
    ont
    -0.15
    aggio
    -0.15
    haled
    -0.15
    illet
    -0.15
    headline
    -0.14
    207
    -0.14
    y
    -0.14
    iac
    -0.14
    POSITIVE LOGITS
    ters
    0.43
    ting
    0.31
    tings
    0.29
    TING
    0.23
     down
    0.22
    tdown
    0.22
    ty
    0.22
    TER
    0.21
    tl
    0.21
     doors
    0.21
    Act Density 0.008%

    No Known Activations