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

    Neuronpedia

    INDEX
    Explanations

    HTML code elements

    oai_token-act-pair · gpt-3.5-turbo

    elements related to HTML or XML markup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     artificially
    -0.67
     unheard
    -0.66
     dated
    -0.63
     ultras
    -0.63
     Thurs
    -0.61
     chlorine
    -0.59
     differential
    -0.59
     creeping
    -0.59
     untouched
    -0.59
    ipop
    -0.58
    POSITIVE LOGITS
     ACTIONS
    0.94
    ########
    0.84
    ////////////////////////////////
    0.83
     ###
    0.81
    ################################
    0.81
    ####
    0.79
    ----------------------------------------------------------------
    0.79
    ////////
    0.79
    ï¸
    0.78
    --------------------------------------------------------
    0.77
    Act Density 0.079%

    No Known Activations