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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "shown" and related showcasing expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĬãĤĬ
    -0.18
    ated
    -0.18
    ating
    -0.16
    asm
    -0.16
    zsche
    -0.15
    toi
    -0.15
     shown
    -0.15
    zon
    -0.15
    ãĥ³ãĥģ
    -0.14
    omik
    -0.14
    POSITIVE LOGITS
    manship
    0.27
    rooms
    0.25
     forth
    0.23
    runner
    0.21
    piece
    0.20
    cased
    0.20
    biz
    0.20
    cases
    0.19
    ings
    0.19
    -hide
    0.18
    Act Density 0.036%

    No Known Activations