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

    Neuronpedia

    INDEX
    Explanations

    words related to time references or life stages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     {\↵
    -0.15
    Ī
    -0.15
    erg
    -0.14
    ева
    -0.14
    ÑĪиÑĢ
    -0.14
    ayer
    -0.14
    æ¿
    -0.14
     sna
    -0.14
    oris
    -0.14
    rez
    -0.13
    POSITIVE LOGITS
    rial
    0.16
    licht
    0.16
    /GPL
    0.16
    esser
    0.16
    Ñij
    0.14
    bruar
    0.14
    ноз
    0.14
    Ø°
    0.14
    pler
    0.14
    _LT
    0.13
    Act Density 0.039%

    No Known Activations