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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles indicating ongoing actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compliment
    -0.73
     Surprise
    -0.69
     retiring
    -0.64
    sole
    -0.62
    behind
    -0.62
    contin
    -0.62
     congratulated
    -0.61
    fortunately
    -0.60
    vm
    -0.59
     Marcos
    -0.59
    POSITIVE LOGITS
     circuits
    0.71
     anew
    0.71
    ury
    0.69
    edIn
    0.67
     defenses
    0.66
    RAY
    0.64
    aband
    0.64
    ittle
    0.63
     quotas
    0.62
     adolesc
    0.62
    Act Density 0.136%

    No Known Activations