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

    Neuronpedia

    INDEX
    Explanations

    special characters like 'Ċ' and 'Ŀ'

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     satell
    -0.83
     covenant
    -0.77
     periodic
    -0.76
     describ
    -0.75
     tast
    -0.74
     speeding
    -0.73
     neighb
    -0.73
     phased
    -0.71
     fermented
    -0.68
     treat
    -0.67
    POSITIVE LOGITS
    Advertisements
    1.28
    âĢ¢
    1.28
    ###
    1.23
    =-=-=-=-=-=-=-=-
    1.21
    âĹı
    1.20
    #
    1.20
    ·
    1.16
    ©
    1.15
    ________________________________________________________________
    1.15
    --------------------------------------------------------
    1.15
    Act Density 0.367%

    No Known Activations