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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers and titles related to events or rules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nah
    -0.15
    STANCE
    -0.14
    Ń
    -0.14
    cka
    -0.13
     pestic
    -0.13
    ĥĿ
    -0.13
    ñ
    -0.13
    orr
    -0.13
    478
    -0.13
    rost
    -0.13
    POSITIVE LOGITS
    2
    0.36
    Û²
    0.26
    äºĮ
    0.25
     äºĮ
    0.24
    âij¡
    0.24
    ï¼Ĵ
    0.24
    २
    0.23
    âĤĤ
    0.23
     Two
    0.23
     Second
    0.23
    Act Density 0.177%

    No Known Activations