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

    Neuronpedia

    INDEX
    Explanations

    numerical values with an emphasis on fractions and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their relationships in contexts like statistics or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    —
    -0.72
    ,—
    -0.72
    ,[
    -0.70
    ;
    -0.69
    ,
    -0.69
    ,'
    -0.68
    ?
    -0.67
     âĢķ
    -0.67
    ––
    -0.66
    >,
    -0.65
    POSITIVE LOGITS
    imentary
    0.57
    bernatorial
    0.56
    lesiastical
    0.53
     havoc
    0.52
    imental
    0.51
    ileged
    0.50
    osponsors
    0.50
    ravings
    0.50
    çĶ°
    0.49
    izens
    0.49
    Act Density 1.008%

    No Known Activations