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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement or progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undler
    -0.20
    prak
    -0.17
    ä»ĺ
    -0.14
    EDIUM
    -0.14
    -être
    -0.14
    hap
    -0.14
    icious
    -0.14
    hack
    -0.13
    odore
    -0.13
    anzi
    -0.13
    POSITIVE LOGITS
    wards
    0.21
    /down
    0.18
    /off
    0.16
    swing
    0.16
    ery
    0.15
    /up
    0.14
    nings
    0.13
    erc
    0.13
    WARDS
    0.13
    иÑĢÑĥ
    0.13
    Act Density 0.310%

    No Known Activations