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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotion and reflection on experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isson
    -0.19
     fixed
    -0.15
    rane
    -0.15
    onian
    -0.14
    ↵
    -0.14
     Scho
    -0.14
    endale
    -0.14
    Fixed
    -0.14
    lov
    -0.14
    rene
    -0.13
    POSITIVE LOGITS
    moid
    0.15
    expo
    0.15
    anta
    0.15
    mercial
    0.14
    uyen
    0.14
    antha
    0.14
     —↵↵
    0.14
     plur
    0.14
     TSR
    0.13
    /**č↵
    0.13
    Act Density 0.262%

    No Known Activations