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

    Neuronpedia

    INDEX
    Explanations

    references to conditions of being or temporal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ssid
    -0.17
    uts
    -0.17
    agli
    -0.15
    tright
    -0.15
    iale
    -0.15
    JNI
    -0.15
    ews
    -0.14
    {}
    -0.14
     Bart
    -0.14
    _firestore
    -0.14
    POSITIVE LOGITS
    lover
    0.17
    äl
    0.17
    owo
    0.16
    ierge
    0.16
    apy
    0.15
    pyx
    0.15
     Cherry
    0.15
     bump
    0.14
     nothing
    0.14
    izen
    0.14
    Act Density 0.001%

    No Known Activations