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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and definitions in a formatted structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amu
    -0.16
    æł¸
    -0.15
    endale
    -0.15
    fi
    -0.15
    alah
    -0.15
    orde
    -0.14
    orum
    -0.14
    обÑĢаз
    -0.14
    lander
    -0.14
    adar
    -0.14
    POSITIVE LOGITS
    holm
    0.17
     Verg
    0.15
    rical
    0.14
    лиÑĪ
    0.14
    als
    0.14
    &&(
    0.14
    é¦Ļ
    0.13
    829
    0.13
     Cousins
    0.13
     Brothers
    0.13
    Act Density 0.060%

    No Known Activations