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

    Neuronpedia

    INDEX
    Explanations

    references to the letter "Y" or its variations across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieg
    -0.16
    iero
    -0.15
    ief
    -0.15
    leston
    -0.15
    390
    -0.15
    adece
    -0.14
    adors
    -0.14
    ÃŁe
    -0.14
    icher
    -0.14
    моÑģ
    -0.14
    POSITIVE LOGITS
    achts
    0.23
    ea
    0.23
    eh
    0.21
    ves
    0.21
    ez
    0.19
    acht
    0.19
    ields
    0.19
    asmine
    0.19
    atra
    0.19
    psilon
    0.19
    Act Density 0.042%

    No Known Activations