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

    Neuronpedia

    INDEX
    Explanations

    numeric indicators related to requirements and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aku
    -0.17
    ibern
    -0.14
     Lover
    -0.13
    ivet
    -0.13
    ŃIJ
    -0.13
    ãĥĨãĥ«
    -0.13
    CellStyle
    -0.13
    illy
    -0.13
    osti
    -0.13
    bo
    -0.13
    POSITIVE LOGITS
    ÑĥÑĩа
    0.15
    ãĥ¼ãĥĢ
    0.15
    -dismiss
    0.14
    лод
    0.14
    AppState
    0.14
    ãģĵãģ¨
    0.14
     davon
    0.13
    вÑĢоп
    0.13
    ughter
    0.13
    563
    0.13
    Act Density 0.011%

    No Known Activations