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

    Neuronpedia

    INDEX
    Explanations

    words related to categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Evidence
    -0.15
     TBD
    -0.14
     evidence
    -0.14
     Hats
    -0.14
     Platinum
    -0.14
     Nit
    -0.13
    ussen
    -0.13
    ellen
    -0.13
     py
    -0.13
    elden
    -0.13
    POSITIVE LOGITS
    /classes
    0.16
    öst
    0.15
    adera
    0.15
    à¤Ĺल
    0.15
    ochen
    0.14
     thù
    0.14
    pron
    0.14
    ê°Ħ
    0.14
    aż
    0.13
    horn
    0.13
    Act Density 0.006%

    No Known Activations