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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain statistics, findings, or significant figures related to reports or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oon
    -0.15
    onian
    -0.14
    ammen
    -0.14
    URAL
    -0.14
    idl
    -0.13
    oth
    -0.13
    ITU
    -0.13
    ÅĻad
    -0.13
    vor
    -0.13
    ICLE
    -0.13
    POSITIVE LOGITS
    suspend
    0.14
    itbart
    0.14
    ½Ķ
    0.14
     tiêu
    0.14
    ayet
    0.14
    isco
    0.13
    íĥ
    0.13
    æį·
    0.13
    rych
    0.13
    ndl
    0.13
    Act Density 0.388%

    No Known Activations