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

    Neuronpedia

    INDEX
    Explanations

    expressions of clarity and obviousness in arguments or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.17
    ray
    -0.16
    abilit
    -0.15
    INET
    -0.15
     whole
    -0.15
    reen
    -0.14
    worth
    -0.14
    UPPORTED
    -0.14
    ighth
    -0.14
     blank
    -0.14
    POSITIVE LOGITS
    mente
    0.20
    ely
    0.17
    ness
    0.15
    iveness
    0.15
    ly
    0.15
    ously
    0.15
    asion
    0.15
     rÃłng
    0.15
    วà¸Ķ
    0.14
    ugins
    0.14
    Act Density 0.033%

    No Known Activations