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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gaining or having control over a situation or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    o
    -0.16
    olph
    -0.14
    elli
    -0.14
    ussian
    -0.14
    ERA
    -0.14
     gums
    -0.14
    iste
    -0.14
    rada
    -0.14
    Äĵ
    -0.13
    eing
    -0.13
    POSITIVE LOGITS
    аниÑĨ
    0.20
    cosa
    0.15
    igram
    0.15
    urge
    0.15
    ζη
    0.15
    ighton
    0.14
    ÄĽj
    0.14
    ÅĻen
    0.14
    еж
    0.14
    ERGE
    0.14
    Act Density 0.021%

    No Known Activations