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

    Neuronpedia

    INDEX
    Explanations

    references to "World" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibt
    -0.15
    dfs
    -0.15
    墨
    -0.15
     world
    -0.15
    /plain
    -0.14
    ecek
    -0.14
     pathMatch
    -0.14
     Král
    -0.14
    halt
    -0.14
    ibern
    -0.14
    POSITIVE LOGITS
     Wide
    0.26
     Bank
    0.24
    Wide
    0.23
    -wide
    0.21
     wide
    0.21
    -Class
    0.20
     bank
    0.19
    wide
    0.19
    -class
    0.19
    urette
    0.19
    Act Density 0.021%

    No Known Activations