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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to transformations and significant changes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jewel
    -0.16
    eward
    -0.16
    inkel
    -0.16
    uD
    -0.15
    inherits
    -0.15
    iais
    -0.15
    ãģĿ
    -0.14
    iro
    -0.14
    inel
    -0.14
    bens
    -0.14
    POSITIVE LOGITS
    öh
    0.22
    103
    0.16
    é
    0.16
    _printf
    0.15
    itution
    0.15
    101
    0.14
     Personnel
    0.14
     tack
    0.14
    ansson
    0.14
     cle
    0.14
    Act Density 0.016%

    No Known Activations