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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases that introduce new ideas or concepts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "think of" followed by various contexts or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ante
    -0.67
    pite
    -0.64
     cess
    -0.63
     commanded
    -0.61
    anwhile
    -0.61
    Demand
    -0.61
    ollah
    -0.59
     promoter
    -0.59
     recovers
    -0.58
     subsequ
    -0.58
    POSITIVE LOGITS
    thood
    0.71
    agram
    0.69
    gil
    0.68
    ¥µ
    0.67
    ĸ
    0.66
    psc
    0.65
    èĪ
    0.62
     Miko
    0.62
    uben
    0.62
     è£ıè
    0.61
    Act Density 0.048%

    No Known Activations