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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to duality or items that exhibit dual characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzz
    -0.15
    agli
    -0.15
    ese
    -0.14
    jav
    -0.14
    boy
    -0.14
    ijken
    -0.14
    esh
    -0.14
    ug
    -0.14
    emi
    -0.14
    editary
    -0.14
    POSITIVE LOGITS
    -purpose
    0.19
     Hlav
    0.16
    ities
    0.15
     purpose
    0.15
    haps
    0.14
    phem
    0.14
    ilty
    0.14
    /single
    0.14
    iteral
    0.14
    atter
    0.14
    Act Density 0.007%

    No Known Activations