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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditional statements and their outcomes in programming or logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Restr
    -0.17
     Citadel
    -0.16
    fers
    -0.15
    emoc
    -0.15
     Appearance
    -0.15
    ÑĪиÑģÑĮ
    -0.15
    vers
    -0.15
    ak
    -0.14
    athi
    -0.14
     appearance
    -0.14
    POSITIVE LOGITS
    .UIManager
    0.15
    hled
    0.15
     Sparks
    0.15
    edl
    0.14
    è£ķ
    0.14
    hetto
    0.14
    ¯
    0.14
    -toggler
    0.14
    ully
    0.14
    éĨ
    0.14
    Act Density 0.027%

    No Known Activations