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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives related to physical attributes and conditions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    VIAF
    -0.88
    featureID
    -0.85
     Waray
    -0.82
    parsedMessage
    -0.75
     Roskov
    -0.70
     CreateTagHelper
    -0.70
     <",
    -0.69
    WriteAttribute
    -0.69
     doInBackground
    -0.67
     GenerationType
    -0.66
    POSITIVE LOGITS
     recent
    0.56
    orithmic
    0.52
    ness
    0.46
     intest
    0.46
    ginous
    0.45
     especially
    0.44
     critical
    0.44
    4
    0.44
    ro
    0.43
     particularly
    0.43
    Act Density 0.003%

    No Known Activations