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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal reflection and emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atk
    -0.15
    jedn
    -0.15
    jong
    -0.15
    aler
    -0.14
    loff
    -0.14
     ActionTypes
    -0.14
    ERM
    -0.14
     meille
    -0.14
    ucer
    -0.14
    clair
    -0.14
    POSITIVE LOGITS
    gesi
    0.14
     Sink
    0.14
    οÏģ
    0.14
    rie
    0.14
     autogenerated
    0.14
    á»ĵ
    0.13
    din
    0.13
     út
    0.13
    kest
    0.13
     Suspension
    0.13
    Act Density 0.587%

    No Known Activations