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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong affirmation or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gid
    -0.16
    age
    -0.16
    egr
    -0.15
    ei
    -0.15
    gomery
    -0.15
    Ïĩα
    -0.14
    reh
    -0.14
    ej
    -0.14
    ebb
    -0.14
    AGE
    -0.14
    POSITIVE LOGITS
     Frid
    0.16
    ippers
    0.15
     Barber
    0.15
    itchen
    0.15
    forcements
    0.14
    isky
    0.14
    opor
    0.14
    _nth
    0.14
    lear
    0.14
    ÑĤик
    0.14
    Act Density 0.105%

    No Known Activations