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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heny
    -0.72
    osponsors
    -0.70
    xton
    -0.67
    hips
    -0.66
    inders
    -0.62
    ories
    -0.62
    owed
    -0.61
    orically
    -0.61
    atted
    -0.60
    ivated
    -0.59
    POSITIVE LOGITS
    esan
    0.89
     Hundred
    0.82
     hundred
    0.74
     sided
    0.74
    stice
    0.69
     handed
    0.68
     dimensional
    0.68
    hots
    0.67
    uscript
    0.65
    alian
    0.65
    Act Density 0.055%

    No Known Activations