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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "only."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Matheson
    -0.65
     devrez
    -0.63
     milagro
    -0.62
     Nunn
    -0.61
     urbaine
    -0.61
     hiburan
    -0.60
    Vex
    -0.59
     Wadsworth
    -0.58
    ]=\
    -0.58
    ());
    -0.57
    POSITIVE LOGITS
    SBATCH
    0.91
    0.82
    #+#
    0.77
     Capp
    0.65
     يتيمه
    0.64
    crl
    0.63
    kaŭ
    0.62
    tería
    0.62
    pushFollow
    0.62
    cinfo
    0.61
    Act Density 0.094%

    No Known Activations