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

    Neuronpedia

    INDEX
    Explanations

    questions and reflections on existential and ethical dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.40
    μη
    -0.40
    ﾉ
    -0.39
    de
    -0.39
    kr
    -0.38
    相反
    -0.36
    واد
    -0.36
    ✭
    -0.36
     conmigo
    -0.36
    zet
    -0.35
    POSITIVE LOGITS
     really
    1.54
     truly
    1.44
    really
    1.40
     realmente
    1.37
     wirklich
    1.34
    truly
    1.32
     Really
    1.31
     vraiment
    1.30
     réellement
    1.30
     actually
    1.26
    Act Density 0.243%

    No Known Activations