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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with evaluation and judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ean
    -0.17
    634
    -0.15
    uto
    -0.14
    §
    -0.14
    uta
    -0.14
    iu
    -0.14
     Classics
    -0.14
    ullets
    -0.14
    787
    -0.14
    ax
    -0.13
    POSITIVE LOGITS
    rosso
    0.20
    ijkstra
    0.16
    OptionsMenu
    0.16
    CACHE
    0.16
    isinde
    0.15
    rech
    0.15
    Å¡ak
    0.15
    esian
    0.15
     mongoose
    0.14
    aldo
    0.14
    Act Density 0.026%

    No Known Activations