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

    Neuronpedia

    INDEX
    Explanations

    names or titles with a comma after them

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.76
    icultural
    -0.69
     incentive
    -0.68
    hesda
    -0.67
    nosis
    -0.65
     slowdown
    -0.65
     knee
    -0.64
     payroll
    -0.64
     impulse
    -0.64
    ritional
    -0.63
    POSITIVE LOGITS
     Mole
    0.76
     aka
    0.76
    SourceFile
    0.75
     abbre
    0.73
     Mechdragon
    0.72
    Appearance
    0.71
    meaning
    0.71
    é¾
    0.71
     Rahman
    0.70
    ãĤ´ãĥ³
    0.67
    Act Density 0.377%

    No Known Activations