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

    Neuronpedia

    INDEX
    Explanations

    themes related to social dynamics and personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ually
    -0.20
    atically
    -0.20
    ziej
    -0.19
    atively
    -0.18
    ymous
    -0.18
    ergic
    -0.18
    GED
    -0.17
    bable
    -0.17
    ially
    -0.16
    ingly
    -0.16
    POSITIVE LOGITS
    ness
    1.16
    ity
    0.85
    NESS
    0.80
    eness
    0.56
    iness
    0.53
    ITY
    0.50
    itude
    0.50
    heid
    0.49
    ality
    0.47
    ism
    0.47
    Act Density 0.192%

    No Known Activations