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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and notation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    InstanceState
    -0.65
    VersionUID
    -0.62
    ariana
    -0.57
    modore
    -0.54
    Formatting
    -0.52
    vettes
    -0.51
    uevas
    -0.50
    cigarettes
    -0.50
    TotalPrice
    -0.49
    KommentareTeilen
    -0.49
    POSITIVE LOGITS
    urlopen
    0.80
     مشين
    0.80
    )):
    0.68
    DockStyle
    0.67
     numberWith
    0.67
     ostavi
    0.67
    reportWebVitals
    0.66
    oa̍t
    0.64
    ]")]
    0.63
    ówn
    0.63
    Act Density 0.055%

    No Known Activations