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

    Neuronpedia

    INDEX
    Explanations

    words related to errors or mistakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     previews
    -0.15
    ifique
    -0.15
    Remarks
    -0.15
    osu
    -0.14
    uye
    -0.14
    æĪ·
    -0.14
    ncy
    -0.14
    uyu
    -0.14
    Ħĸ
    -0.14
    åijĬ
    -0.14
    POSITIVE LOGITS
    208
    0.17
    eng
    0.16
    ech
    0.16
     Echo
    0.15
    es
    0.15
    rib
    0.15
    WM
    0.15
    ler
    0.15
    ļ
    0.14
    anger
    0.14
    Act Density 0.003%

    No Known Activations