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

    Neuronpedia

    INDEX
    Explanations

    references to knowledgeable or skilled individuals in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "experienced."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    corn
    -0.75
    uzzle
    -0.71
    ono
    -0.70
    apo
    -0.67
    ect
    -0.66
    aughter
    -0.66
    hatt
    -0.65
     bloc
    -0.64
    etary
    -0.64
    ococ
    -0.63
    POSITIVE LOGITS
    ienced
    1.11
     experienced
    0.98
    HAEL
    0.91
     experien
    0.82
     veter
    0.74
     Bucc
    0.73
     Experience
    0.71
     LCS
    0.71
    exper
    0.69
     firsthand
    0.69
    Act Density 0.011%

    No Known Activations