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

    Neuronpedia

    INDEX
    Explanations

    traits or features that set something apart or make it unique

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate how something is distinguished or differentiated from others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     commute
    -0.75
    onic
    -0.74
    aft
    -0.71
     vomiting
    -0.68
     spir
    -0.65
    stant
    -0.64
     poisoning
    -0.63
     numb
    -0.63
     draining
    -0.63
    ancel
    -0.63
    POSITIVE LOGITS
    ĸļ
    1.07
     uniqueness
    0.93
    ortment
    0.87
    ¥µ
    0.80
    iqueness
    0.79
     excellence
    0.78
     Achievement
    0.78
     distinguishes
    0.77
    ":"","
    0.76
    Orig
    0.76
    Act Density 0.240%

    No Known Activations