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

    Neuronpedia

    INDEX
    Explanations

    programming interface definitions and method signatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Private
    -0.26
    Private
    -0.25
    PRIVATE
    -0.21
     PRIVATE
    -0.21
     private
    -0.18
    .Private
    -0.18
    .private
    -0.18
    private
    -0.17
    -private
    -0.17
    (private
    -0.16
    POSITIVE LOGITS
     abstract
    0.28
     default
    0.27
    default
    0.25
    abstract
    0.24
     void
    0.23
     interface
    0.21
     defaulted
    0.20
     defaults
    0.20
    void
    0.19
    	default
    0.19
    Act Density 0.019%

    No Known Activations