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

    Neuronpedia

    INDEX
    Explanations

    comparisons or quantity-related statements

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases highlighting differences or similarities among groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istries
    -0.80
    arta
    -0.63
     Properties
    -0.61
    achine
    -0.61
    FTWARE
    -0.56
    akeru
    -0.56
    */(
    -0.56
    £ı
    -0.55
    arios
    -0.55
     QC
    -0.55
    POSITIVE LOGITS
     slightest
    0.90
     usual
    0.85
    average
    0.84
    usual
    0.81
     average
    0.76
     actual
    0.69
     mere
    0.68
    ramids
    0.68
     ordinary
    0.67
     predecessors
    0.65
    Act Density 0.179%

    No Known Activations