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

    Neuronpedia

    INDEX
    Explanations

    instances of enjoyment or positive experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñģли
    -0.17
     enjoying
    -0.16
    drawing
    -0.15
    ching
    -0.15
    owing
    -0.14
    gere
    -0.14
    uras
    -0.14
    older
    -0.14
    odes
    -0.14
    ched
    -0.14
    POSITIVE LOGITS
    ably
    0.36
    able
    0.23
    ments
    0.22
    ment
    0.21
    ables
    0.20
    erals
    0.20
    /dis
    0.20
     themselves
    0.17
     freedoms
    0.16
     being
    0.16
    Act Density 0.041%

    No Known Activations