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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mental states and cognitive processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ileo
    -0.19
    aurus
    -0.19
    antino
    -0.19
    аниÑĨ
    -0.17
    Ķ
    -0.15
    icks
    -0.15
    izzly
    -0.15
    ynthia
    -0.14
    Tween
    -0.14
    gether
    -0.14
    POSITIVE LOGITS
    sets
    0.29
    /body
    0.25
    lessly
    0.24
    space
    0.24
    edly
    0.23
    -body
    0.22
    -set
    0.21
    fulness
    0.21
    ustry
    0.20
    /memory
    0.20
    Act Density 0.055%

    No Known Activations