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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of the word "Box"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Box" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ittee
    -0.73
    IDENT
    -0.67
    opoulos
    -0.67
    asury
    -0.65
    Äĩ
    -0.62
    ETHOD
    -0.62
     infertility
    -0.61
    ASY
    -0.60
     NOTICE
    -0.59
     maj
    -0.59
    POSITIVE LOGITS
    er
    1.21
    es
    1.15
    ertodd
    1.01
    esy
    0.99
    eer
    0.99
    ed
    0.98
    box
    0.95
    eers
    0.92
    door
    0.91
    spring
    0.89
    Act Density 0.015%

    No Known Activations