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

    Neuronpedia

    INDEX
    Explanations

    the word "one" with a strong emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a singular significant item or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.72
    lead
    -0.65
    ategory
    -0.65
    inders
    -0.63
    Range
    -0.63
    ocal
    -0.62
    avascript
    -0.62
    Uncommon
    -0.61
    owed
    -0.61
    photos
    -0.60
    POSITIVE LOGITS
     Hundred
    0.91
    esan
    0.87
     hundred
    0.81
    uscript
    0.73
    stice
    0.73
     handed
    0.71
     sided
    0.69
    ILLE
    0.69
     dimensional
    0.65
    rency
    0.64
    Act Density 0.041%

    No Known Activations