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

    Neuronpedia

    INDEX
    Explanations

    mentions of "high" or "High" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éľ
    -0.16
    OutputStream
    -0.15
    uben
    -0.14
    cco
    -0.14
     nut
    -0.14
    dds
    -0.14
    dition
    -0.14
    entially
    -0.14
    ä¸ģ
    -0.14
    oma
    -0.13
    POSITIVE LOGITS
    school
    0.26
    lander
    0.24
    lands
    0.22
     Noon
    0.21
     school
    0.21
     School
    0.20
    land
    0.20
    -resolution
    0.20
    ways
    0.20
    speed
    0.19
    Act Density 0.061%

    No Known Activations