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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers and labels in a structured format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     (!__
    -0.73
     choque
    -0.70
     Pelosi
    -0.70
    y
    -0.64
    Pes
    -0.64
    lu
    -0.63
     Pes
    -0.61
     Moseley
    -0.60
    ma
    -0.60
    (__
    -0.60
    POSITIVE LOGITS
    ]='\
    0.90
    NOPQRST
    0.87
    ^(@)
    0.85
     arşivlendi
    0.84
    NUMX
    0.83
    cS
    0.82
     &___
    0.82
     inégal
    0.81
     Sina
    0.80
    檚
    0.80
    Act Density 0.110%

    No Known Activations