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

    Neuronpedia

    INDEX
    Explanations

    bracketed or structured elements in code, particularly those involved in imports and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oš
    -0.17
    cott
    -0.16
    437
    -0.16
    AuthService
    -0.15
    anes
    -0.14
    fffffff
    -0.14
    seau
    -0.14
    ija
    -0.13
    jak
    -0.13
    ippo
    -0.13
    POSITIVE LOGITS
     TW
    0.14
    >:</
    0.14
    udent
    0.14
     Warwick
    0.14
     Sok
    0.14
     meter
    0.13
    eg
    0.13
     dil
    0.13
    916
    0.13
     LX
    0.13
    Act Density 0.001%

    No Known Activations