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

    Neuronpedia

    INDEX
    Explanations

    adjectives and past tense verbs that are connected to negative situations

    oai_token-act-pair · gpt-3.5-turbo

    words that convey surprise or unusual circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Solution
    -0.62
     Practices
    -0.59
     Means
    -0.56
     Authorities
    -0.56
     Solution
    -0.56
     Participant
    -0.56
    SHIP
    -0.55
     examiner
    -0.53
    ynski
    -0.52
    OTOS
    -0.52
    POSITIVE LOGITS
    iously
    1.09
    ishly
    1.08
    uously
    1.02
    ingly
    0.95
    ifully
    0.95
    ily
    0.90
    oused
    0.87
    aciously
    0.86
    efully
    0.86
    inently
    0.85
    Act Density 0.548%

    No Known Activations