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

    Neuronpedia

    INDEX
    Explanations

    references to tours or travel-related activities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    OGND
    -0.52
     placés
    -0.52
    MemoryWarning
    -0.51
    mor
    -0.50
     tr
    -0.49
     mv
    -0.48
    eventbus
    -0.48
    又是
    -0.48
    istoitu
    -0.48
    })));
    -0.48
    POSITIVE LOGITS
     Majefty
    0.69
    Kjelder
    0.65
     Grou
    0.63
    PMailer
    0.60
     ſtate
    0.58
    inSlope
    0.57
     themſelves
    0.57
     itſelf
    0.56
    mặt
    0.55
    wiſe
    0.55
    Act Density 0.001%

    No Known Activations