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

    Neuronpedia

    INDEX
    Explanations

    phrases related to placeholders or markers indicating the absence of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oux
    -0.15
    anko
    -0.15
     thinking
    -0.15
    Filled
    -0.14
    ERIC
    -0.14
    éĿ©
    -0.14
     Cru
    -0.14
     Buch
    -0.14
     Bran
    -0.14
    LD
    -0.14
    POSITIVE LOGITS
    arser
    0.16
    alom
    0.16
    eya
    0.16
    ICON
    0.15
    reator
    0.15
    вÑĸÑĤ
    0.15
    ená
    0.14
    tdown
    0.14
    decorators
    0.14
    eda
    0.14
    Act Density 0.000%

    No Known Activations