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

    Neuronpedia

    INDEX
    Explanations

    references to lists or definitions in a structured format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Garrick
    -0.81
     Shiva
    -0.76
    Shiva
    -0.75
     Salvador
    -0.75
     Kass
    -0.74
     Oakley
    -0.73
    casio
    -0.73
    meau
    -0.73
     Nixon
    -0.71
     Ernesto
    -0.71
    POSITIVE LOGITS
    DL
    1.27
    dl
    1.22
     DL
    1.20
     dl
    1.05
    Dl
    0.77
    KX
    0.71
    theless
    0.69
    Portale
    0.69
    ύν
    0.68
     Zinn
    0.66
    Act Density 0.005%

    No Known Activations