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

    Neuronpedia

    INDEX
    Explanations

    mention of sequences or groups identified as "series."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    series
    -0.21
    ìĦľ
    -0.20
    ìĦľëĬĶ
    -0.20
    ager
    -0.19
    soever
    -0.19
    ç³»åĪĹ
    -0.18
    agers
    -0.17
    amura
    -0.17
    ERS
    -0.17
    _series
    -0.17
    POSITIVE LOGITS
    '
    0.24
    ’
    0.24
    es
    0.20
     finale
    0.19
    icals
    0.18
    -wide
    0.17
    -ending
    0.16
     opener
    0.16
    gue
    0.15
    esz
    0.15
    Act Density 0.042%

    No Known Activations