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

    Neuronpedia

    INDEX
    Explanations

    verbs and their variations indicating actions or states regarding societal issues, particularly concerning injustice or significant actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erk
    -0.16
     Sav
    -0.16
    Ľ
    -0.15
     grantResults
    -0.15
    .mj
    -0.15
    ëĭĿ
    -0.15
    еÑĢп
    -0.14
     Nag
    -0.14
    æ¥ļ
    -0.14
    arms
    -0.14
    POSITIVE LOGITS
    odox
    0.17
     Levin
    0.16
     centrif
    0.15
    RIA
    0.14
    ient
    0.14
    chwitz
    0.14
    sein
    0.14
     Env
    0.13
    heet
    0.13
     env
    0.13
    Act Density 0.377%

    No Known Activations