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

    Neuronpedia

    INDEX
    Explanations

    references to public statements made in formal settings such as interviews and speeches

    oai_token-act-pair · gpt-3.5-turbo

    references to interviews and speeches in the context of political or public statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ''.
    -0.56
    wd
    -0.54
    angs
    -0.54
    }}}
    -0.53
    pes
    -0.53
    default
    -0.52
    .''.
    -0.51
     edges
    -0.51
    =#
    -0.50
    udic
    -0.50
    POSITIVE LOGITS
    that
    1.08
     that
    1.07
    :"
    0.78
     "âĢ¦
    0.77
     "[
    0.76
     how
    0.74
     whether
    0.71
     why
    0.71
    è¦ļéĨĴ
    0.70
     "'
    0.70
    Act Density 0.206%

    No Known Activations