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

    Neuronpedia

    INDEX
    Explanations

    the term "opposite" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Walkover
    -0.69
    JsonKey
    -0.69
    Controllo
    -0.67
    tellten
    -0.66
     мәкалә
    -0.65
     ​​
    -0.63
    uxxxx
    -0.63
    ftagPool
    -0.63
    colhead
    -0.62
     createdBy
    -0.62
    POSITIVE LOGITS
    WebVitals
    0.90
     PPM
    0.89
     ſtate
    0.85
     Vantage
    0.82
     Monfieur
    0.81
     Zab
    0.80
    PLE
    0.79
     Eſ
    0.79
     ainfi
    0.79
     Majefty
    0.76
    Act Density 0.004%

    No Known Activations