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

    Neuronpedia

    INDEX
    Explanations

    names or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    specific proper nouns or unique identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     proble
    -0.80
     assum
    -0.70
     contrace
    -0.68
     اÙĦ
    -0.68
     treasury
    -0.66
     conduc
    -0.66
     intimid
    -0.66
     princ
    -0.66
     bible
    -0.66
    è¦ļéĨĴ
    -0.65
    POSITIVE LOGITS
    bol
    0.81
    lesh
    0.80
    anth
    0.79
    ja
    0.78
    osa
    0.77
    nos
    0.77
    aro
    0.76
    ella
    0.76
    vier
    0.75
     Budd
    0.74
    Act Density 0.847%

    No Known Activations