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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frick
    -0.86
    -0.76
    gridx
    -0.75
     Grease
    -0.74
    Dieter
    -0.71
     koper
    -0.71
     Giz
    -0.70
     Italijanski
    -0.68
    unhofer
    -0.67
     Ghi
    -0.67
    POSITIVE LOGITS
     urbanas
    0.85
     Martine
    0.82
     Sabina
    0.78
     xmax
    0.77
     Pokies
    0.76
    wanzig
    0.74
     vPvB
    0.74
     xxiv
    0.74
     XXII
    0.73
     XXV
    0.72
    Act Density 0.429%

    No Known Activations