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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ben
    -0.24
    brit
    -0.23
     bureau
    -0.22
    bu
    -0.22
     benz
    -0.22
    bra
    -0.22
    bob
    -0.21
    bum
    -0.20
     br
    -0.20
    bil
    -0.20
    POSITIVE LOGITS
    -B
    0.53
    _B
    0.48
    	B
    0.40
    ,B
    0.38
    ÂłB
    0.37
    (B
    0.36
     Ðij
    0.36
    .B
    0.35
    ÂłÐij
    0.34
    -Ðij
    0.34
    Act Density 0.133%

    No Known Activations