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

    Neuronpedia

    INDEX
    Explanations

    instances of time-related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osate
    -0.17
    essim
    -0.15
    etu
    -0.15
    ÑĦеÑĢ
    -0.14
    orgh
    -0.14
    ama
    -0.14
    boro
    -0.14
    agh
    -0.14
    ogg
    -0.14
    Ĭ
    -0.14
    POSITIVE LOGITS
    ury
    0.18
    öst
    0.16
    OTS
    0.15
    roz
    0.14
    _dirty
    0.14
     mah
    0.14
    Anywhere
    0.13
     topl
    0.13
     fal
    0.13
    Mah
    0.13
    Act Density 0.010%

    No Known Activations