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

    Neuronpedia

    INDEX
    Explanations

    language and phrases regarding transformations and significant changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.59
    RegressionTest
    -0.57
    TRAILING
    -0.54
    ConstraintMaker
    -0.48
    DataMember
    -0.47
    ücksich
    -0.47
    PreExecute
    -0.47
    urlopen
    -0.43
    ẫu
    -0.43
    łosi
    -0.42
    POSITIVE LOGITS
     world
    3.06
    world
    2.55
     mundo
    2.19
     WORLD
    2.13
     universe
    2.05
    世界
    2.04
     World
    2.04
     worlds
    2.04
    World
    1.99
    WORLD
    1.98
    Act Density 0.366%

    No Known Activations