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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and discussions around choice or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leon
    -0.18
    olulu
    -0.15
    metros
    -0.14
    utch
    -0.14
     exc
    -0.14
    conto
    -0.14
    346
    -0.14
    leme
    -0.14
    _PA
    -0.14
    utow
    -0.14
    POSITIVE LOGITS
    oft
    0.15
    avad
    0.15
    rava
    0.15
    uci
    0.15
    rav
    0.15
    .soft
    0.14
    Backing
    0.14
    ัà¸ĩส
    0.14
    .persist
    0.14
     Sunder
    0.14
    Act Density 0.199%

    No Known Activations