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

    Neuronpedia

    INDEX
    Explanations

    adverbs or phrases conveying absolute certainty

    oai_token-act-pair · gpt-3.5-turbo

    the word "absolutely" and its variations in emphatic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.87
    engers
    -0.82
    ulative
    -0.81
    board
    -0.80
    enegger
    -0.76
    sonian
    -0.76
    NetMessage
    -0.75
    ulton
    -0.74
    nan
    -0.72
    pring
    -0.72
    POSITIVE LOGITS
    ove
    0.65
    reme
    0.65
     annihil
    0.64
     devast
    0.63
     qualitative
    0.63
     monarchy
    0.63
     delighted
    0.62
     defin
    0.62
     exempt
    0.62
     positioned
    0.62
    Act Density 0.015%

    No Known Activations