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

    Neuronpedia

    INDEX
    Explanations

    references to guest appearances or participation in events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertz
    -0.18
    ãģ£ãģ±
    -0.17
    zes
    -0.16
    ossa
    -0.15
    annes
    -0.15
    thal
    -0.15
    abeth
    -0.15
    ainen
    -0.14
    udit
    -0.14
     carr
    -0.14
    POSITIVE LOGITS
    imates
    0.23
    imate
    0.23
    imating
    0.22
    imator
    0.21
     appearances
    0.20
     speakers
    0.20
    house
    0.19
    imated
    0.19
    imation
    0.19
     appearance
    0.19
    Act Density 0.015%

    No Known Activations