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

    Neuronpedia

    INDEX
    Explanations

    phrases related to processes, changes, and movements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersions
    -0.14
    UpInside
    -0.14
     shorter
    -0.14
    kân
    -0.14
    çŀ¬
    -0.14
     ëĭ¹ìĭľ
    -0.14
     upstream
    -0.13
    antz
    -0.13
     Opportunities
    -0.13
     huy
    -0.13
    POSITIVE LOGITS
     slowly
    0.52
     slow
    0.48
    slow
    0.47
    Slow
    0.46
     Slow
    0.46
     gradual
    0.45
     gradually
    0.42
     progress
    0.39
    progress
    0.37
    _slow
    0.35
    Act Density 0.037%

    No Known Activations