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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making a comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "say."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stra
    -0.67
     Siber
    -0.60
    olated
    -0.60
    ATURE
    -0.59
     Instruments
    -0.59
    vernight
    -0.58
    olate
    -0.56
    itol
    -0.56
    ļéĨĴ
    -0.55
    peria
    -0.55
    POSITIVE LOGITS
     uh
    1.30
     um
    1.27
     say
    1.15
     oh
    1.08
    say
    1.06
    wait
    1.02
     gasp
    1.01
     ah
    1.01
     well
    0.93
     er
    0.92
    Act Density 0.096%

    No Known Activations