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

    Neuronpedia

    INDEX
    Explanations

    conversational affirmations and informal agreement expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppers
    -0.16
    bum
    -0.16
    anton
    -0.15
    пов
    -0.15
    ables
    -0.14
    ateg
    -0.14
     Ñģобой
    -0.14
    legen
    -0.14
     inout
    -0.14
    olen
    -0.14
    POSITIVE LOGITS
    elo
    0.19
    ernes
    0.15
    gross
    0.14
     ass
    0.14
    wicklung
    0.14
    -widgets
    0.14
    asl
    0.14
    flush
    0.14
    udi
    0.13
     reservation
    0.13
    Act Density 0.052%

    No Known Activations