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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers typically associated with online content or accounts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    roek
    -0.64
    twimg
    -0.62
    Xna
    -0.59
    ufig
    -0.58
     صوتيه
    -0.57
    unhofer
    -0.56
     distanciation
    -0.55
    ésil
    -0.55
     المعيارى
    -0.55
     Económica
    -0.54
    POSITIVE LOGITS
    resave
    0.63
    antMatchers
    0.48
     deserted
    0.47
    #+#
    0.46
    Mean
    0.46
     mean
    0.45
    means
    0.45
    fromLTRB
    0.45
    mean
    0.44
     prey
    0.44
    Act Density 0.002%

    No Known Activations