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

    Neuronpedia

    INDEX
    Explanations

    file paths and directories

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     far
    -0.59
     cá
    -0.59
     home
    -0.59
     Ven
    -0.57
    bakken
    -0.56
     deli
    -0.54
     pap
    -0.54
     cla
    -0.54
     Serikat
    -0.54
     بيها
    -0.53
    POSITIVE LOGITS
     feroit
    0.91
     étoient
    0.88
     auroit
    0.83
    OGND
    0.82
     avoient
    0.81
     "..\..\..\
    0.80
    IntoConstraints
    0.80
     plufieurs
    0.79
    PerformLayout
    0.78
     fhort
    0.77
    Act Density 0.007%

    No Known Activations