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

    Neuronpedia

    INDEX
    Explanations

    expressions that indicate positive additions or enhancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bak
    -0.15
    ë»
    -0.14
    presso
    -0.14
    tur
    -0.14
    als
    -0.14
    anel
    -0.14
    -Token
    -0.14
    /me
    -0.13
    itz
    -0.13
    ipe
    -0.13
    POSITIVE LOGITS
    ieres
    0.18
    ieurs
    0.15
    zier
    0.14
    ++++++++++++++++++++++++++++++++
    0.14
    SelectedItem
    0.14
    ãĥªãĤ¢
    0.14
    /sub
    0.14
    ë¡ľëĬĶ
    0.14
    941
    0.14
    olla
    0.13
    Act Density 0.018%

    No Known Activations