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

    Neuronpedia

    INDEX
    Explanations

    substantive nouns following the word "finding."

    oai_token-act-pair · gpt-3.5-turbo

    the concept of searching for specific items or solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceive
    -0.73
    heid
    -0.72
    eatures
    -0.70
    ared
    -0.64
    cribed
    -0.63
    SIGN
    -0.62
     thanked
    -0.61
    adoes
    -0.61
     ceremon
    -0.61
    cription
    -0.60
    POSITIVE LOGITS
    ById
    1.05
    bleacher
    0.77
    irlfriend
    0.70
     è£ıè
    0.69
    arrett
    0.69
     refuge
    0.68
     Haku
    0.67
     effic
    0.65
     foothold
    0.65
     elusive
    0.65
    Act Density 0.196%

    No Known Activations