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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     proper
    -0.17
     Austr
    -0.16
    zte
    -0.15
    ingu
    -0.15
    aje
    -0.15
     candid
    -0.15
    adb
    -0.15
    ære
    -0.14
     surre
    -0.14
    ackbar
    -0.14
    POSITIVE LOGITS
    kowski
    0.18
    Ïĩαν
    0.15
     stamped
    0.15
    å¡
    0.15
    apon
    0.14
    dbl
    0.14
    ↵↵
    0.14
    892
    0.14
    dbus
    0.14
    505
    0.14
    Act Density 0.140%

    No Known Activations