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

    Neuronpedia

    INDEX
    Explanations

    expressions of environmental actions and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingles
    -0.16
    aleb
    -0.15
    incare
    -0.14
    ="../../../
    -0.14
    ACES
    -0.14
    ungs
    -0.14
    ToBounds
    -0.14
    ÙĦات
    -0.14
    pany
    -0.13
    ulg
    -0.13
    POSITIVE LOGITS
     harness
    0.15
    issan
    0.15
     Clo
    0.15
     Ä°z
    0.14
     Bram
    0.14
    pector
    0.13
    ushman
    0.13
    Filed
    0.13
     Gest
    0.13
     sát
    0.13
    Act Density 0.004%

    No Known Activations