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

    Neuronpedia

    INDEX
    Explanations

    words related to the function or operation of systems or objects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "function" and its variations, indicating operational capacity or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cott
    -0.80
     Harriet
    -0.65
     Jed
    -0.65
     quotes
    -0.64
     Uri
    -0.64
    CU
    -0.63
    yu
    -0.63
     Lank
    -0.62
     Lyn
    -0.62
     Gale
    -0.62
    POSITIVE LOGITS
    ality
    1.02
    ational
    0.95
    ative
    0.92
    aries
    0.92
    ional
    0.90
    ivity
    0.86
    abilities
    0.79
    alities
    0.78
    ives
    0.78
    ally
    0.77
    Act Density 0.041%

    No Known Activations