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

    Neuronpedia

    INDEX
    Explanations

    numerical values and code-specific syntactic structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gon
    -0.15
     Conn
    -0.14
    KNOWN
    -0.14
    elez
    -0.14
     responsibility
    -0.13
    rvé
    -0.13
     Freed
    -0.13
    _rb
    -0.13
    Inject
    -0.13
    بÙĪ
    -0.13
    POSITIVE LOGITS
    ickname
    0.16
    ulk
    0.15
    irit
    0.15
    toolbox
    0.15
    ABCDEFGHIJKLMNOP
    0.15
    ëĿ¼ëıĦ
    0.15
    اÙĦت
    0.15
    akat
    0.15
    erken
    0.14
    quist
    0.14
    Act Density 0.101%

    No Known Activations