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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ("
    -0.18
    633
    -0.15
    Aside
    -0.15
     Deliver
    -0.15
    091
    -0.15
    {"
    -0.15
     اÙĦسعÙĪدÙĬØ©
    -0.14
    ourg
    -0.14
    avid
    -0.14
    ippo
    -0.14
    POSITIVE LOGITS
    eyen
    0.17
    entric
    0.16
    emain
    0.16
    .scalablytyped
    0.15
    ÑĢад
    0.15
    ctor
    0.15
    ynes
    0.14
    ocz
    0.14
    got
    0.14
     (âĪ
    0.14
    Act Density 0.023%

    No Known Activations