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

    Neuronpedia

    INDEX
    Explanations

    references to contributions or roles played by individuals in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Ani
    -0.59
     not
    -0.58
     so
    -0.56
     Bent
    -0.54
    idalgo
    -0.54
    mete
    -0.53
     b
    -0.52
    óg
    -0.52
    isses
    -0.51
     firebase
    -0.51
    POSITIVE LOGITS
     itſelf
    1.00
     myſelf
    0.88
    Попис
    0.84
    TextHelper
    0.83
    WebVitals
    0.82
     houſe
    0.82
     Grecian
    0.82
    Vidite
    0.81
     Houſe
    0.79
     ſche
    0.79
    Act Density 0.039%

    No Known Activations