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

    Neuronpedia

    INDEX
    Explanations

    concepts related to numerical significance and countable entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     æħ
    -0.15
    ikan
    -0.15
    gable
    -0.14
    redi
    -0.14
    ágenes
    -0.14
     ÅĻe
    -0.14
    364
    -0.14
    оба
    -0.14
    bones
    -0.14
    iams
    -0.13
    POSITIVE LOGITS
    teen
    0.29
    teenth
    0.26
    rier
    0.19
    zig
    0.17
    -legged
    0.17
    ier
    0.16
    096
    0.15
     dozen
    0.15
    razier
    0.15
    chan
    0.14
    Act Density 0.155%

    No Known Activations