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

    Neuronpedia

    INDEX
    Explanations

    terms related to support and endorsements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hauptartikel
    -0.59
    achet
    -0.47
     Roskov
    -0.42
    してしまった
    -0.42
    owę
    -0.41
    存于互联网档案馆
    -0.40
    stree
    -0.37
    utica
    -0.36
    modelBuilder
    -0.36
     hộ
    -0.36
    POSITIVE LOGITS
    PasswordEncoder
    0.72
    AndEndTag
    0.71
    SBATCH
    0.71
     ſever
    0.69
    httphttps
    0.69
    Ecotoxicity
    0.68
    الحياه
    0.67
     unanimous
    0.66
     fevere
    0.65
     Majefty
    0.64
    Act Density 0.441%

    No Known Activations