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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to comparison

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the phrase "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ograp
    -0.75
    Pg
    -0.74
    bender
    -0.72
    ={
    -0.71
    bernatorial
    -0.66
    few
    -0.64
    obyl
    -0.64
    Guest
    -0.64
    forge
    -0.63
    ](
    -0.62
    POSITIVE LOGITS
     tomorrow
    1.20
     antiquity
    1.06
     today
    1.05
     yesterday
    1.05
     yes
    1.00
     choice
    0.96
     Tomorrow
    0.95
     Appalach
    0.89
     course
    0.86
     1914
    0.85
    Act Density 0.164%

    No Known Activations