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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating knowledge or reaction to information

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating what something is not

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbnail
    -0.71
    ourses
    -0.70
    çļ
    -0.70
    former
    -0.70
    oided
    -0.66
    papers
    -0.63
    WAY
    -0.63
    åº
    -0.62
    send
    -0.60
    ixel
    -0.60
    POSITIVE LOGITS
    icable
    1.12
     uncommon
    1.12
     easy
    1.06
     necessarily
    1.05
     advisable
    1.01
     raining
    1.01
     impossible
    0.95
    eworthy
    0.95
     feasible
    0.92
     surprising
    0.92
    Act Density 0.100%

    No Known Activations