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

    Neuronpedia

    INDEX
    Explanations

    terms related to judgment or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ople
    -0.18
    iage
    -0.15
    leitung
    -0.15
    èŃľ
    -0.15
     Ping
    -0.15
    éné
    -0.14
    okedex
    -0.14
    ields
    -0.14
     defaultManager
    -0.14
    bles
    -0.13
    POSITIVE LOGITS
    bras
    0.15
    impan
    0.15
    Comments
    0.14
    builtin
    0.14
    ÙħÙĨد
    0.14
     WHETHER
    0.13
    atr
    0.13
     builtin
    0.13
    ullan
    0.13
     prag
    0.13
    Act Density 0.041%

    No Known Activations