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

    Neuronpedia

    INDEX
    Explanations

    HTML and JavaScript code snippets

    oai_token-act-pair · gpt-3.5-turbo

    HTML and programming-related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entimes
    -0.73
     coinc
    -0.67
     preservation
    -0.67
    ipop
    -0.63
     undermin
    -0.63
    raviolet
    -0.63
    visor
    -0.63
     outwe
    -0.60
     jealousy
    -0.58
    VIDIA
    -0.58
    POSITIVE LOGITS
     ACTIONS
    0.93
    ###
    0.87
    ####
    0.86
     =================================================================
    0.83
     ###
    0.83
    ï¸
    0.81
    ----------------------------------------------------------------
    0.79
    ////////
    0.79
    ########
    0.79
    --------------------------------------------------------
    0.78
    Act Density 0.065%

    No Known Activations