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

    Neuronpedia

    INDEX
    Explanations

    variable declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _MACRO
    -0.19
    enu
    -0.16
    amac
    -0.14
    aec
    -0.14
    eno
    -0.14
    lander
    -0.14
    ILLE
    -0.14
    nas
    -0.14
    oh
    -0.14
    vari
    -0.13
    POSITIVE LOGITS
     Brill
    0.15
     зад
    0.15
    pec
    0.15
    fitness
    0.14
    éľŀ
    0.14
    Pow
    0.14
     Bund
    0.14
    emm
    0.14
    arel
    0.14
     timber
    0.14
    Act Density 0.004%

    No Known Activations