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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a large portion or quantity of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate quantity or proportion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recip
    -0.69
    EStream
    -0.69
     confir
    -0.66
     stacks
    -0.65
     DISTRICT
    -0.60
    quit
    -0.59
    TOP
    -0.58
    ħĭ
    -0.57
    bid
    -0.57
    Enh
    -0.57
    POSITIVE LOGITS
     course
    0.79
    course
    0.71
    sky
    0.70
    distance
    0.70
    stay
    0.68
    odor
    0.67
     Nort
    0.66
    ourn
    0.65
    pace
    0.63
     Athletic
    0.62
    Act Density 0.072%

    No Known Activations