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

    Neuronpedia

    INDEX
    Explanations

    terms related to filtering and cartridge mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chin
    -0.20
    gear
    -0.19
    iard
    -0.19
    kart
    -0.18
    erson
    -0.18
    etary
    -0.18
    ene
    -0.18
    ij
    -0.18
    ese
    -0.17
    kin
    -0.17
    POSITIVE LOGITS
    ãģ¹ãģį
    0.21
    red
    0.20
    bitrary
    0.20
    mony
    0.18
    riere
    0.17
    cı
    0.17
    bage
    0.16
    rière
    0.16
    ithmetic
    0.16
    iously
    0.16
    Act Density 0.361%

    No Known Activations