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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "be" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.80
    wußt
    -0.73
    extAlignment
    -0.71
    principalColumn
    -0.70
    awtextra
    -0.68
    GeoNames
    -0.67
    multer
    -0.67
    fjspx
    -0.63
     Económica
    -0.62
     MainAxisSize
    -0.62
    POSITIVE LOGITS
     Be
    0.83
    Be
    0.79
    bea
    0.67
    be
    0.67
    BE
    0.64
     BE
    0.64
    bei
    0.56
     Bech
    0.55
     Bef
    0.54
     Bew
    0.53
    Act Density 0.187%

    No Known Activations