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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "box" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opsy
    -0.17
    ustrial
    -0.15
    ufen
    -0.15
    ufs
    -0.15
    opia
    -0.15
    urre
    -0.14
    reich
    -0.14
    icense
    -0.14
    auge
    -0.14
    пÑĢав
    -0.14
    POSITIVE LOGITS
    (es
    0.34
    <dyn
    0.25
    -sizing
    0.24
    ercise
    0.22
    tures
    0.22
    -shadow
    0.20
    (Box
    0.18
    idine
    0.18
    plorer
    0.18
    erif
    0.18
    Act Density 0.029%

    No Known Activations