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

    Neuronpedia

    INDEX
    Explanations

    syntax related to programming functions and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬ģ
    -0.26
    ¬Ĥ
    -0.22
     McB
    -0.22
    fdc
    -0.19
     McGr
    -0.14
    xfb
    -0.14
    afc
    -0.13
    xfd
    -0.13
    xAE
    -0.13
    xEA
    -0.13
    POSITIVE LOGITS
     BB
    0.71
    ı
    0.70
     HH
    0.67
     FF
    0.66
     GG
    0.65
     bb
    0.64
     RR
    0.63
     TT
    0.63
     DD
    0.63
     CC
    0.63
    Act Density 0.785%

    No Known Activations