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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate functionality or service in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .nodeType
    -0.15
    @Web
    -0.15
    _ASSUME
    -0.14
    ORIA
    -0.14
    jes
    -0.13
    ServiceImpl
    -0.13
    _Execute
    -0.13
    HU
    -0.13
    OutOf
    -0.13
    мена
    -0.13
    POSITIVE LOGITS
     function
    0.29
    function
    0.26
     functions
    0.26
     purposes
    0.23
    (function
    0.21
     Functions
    0.21
    functions
    0.20
     Function
    0.20
     dual
    0.20
     serve
    0.19
    Act Density 0.025%

    No Known Activations