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

    Neuronpedia

    INDEX
    Explanations

    expressions of support and demonstration of arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ροφο
    -0.40
     OBSERVATIONS
    -0.40
     discussions
    -0.38
     gossip
    -0.37
     discussion
    -0.37
     sightings
    -0.37
     reported
    -0.36
     debates
    -0.35
    owels
    -0.35
    Bibliography
    -0.35
    POSITIVE LOGITS
    HtmlAttribute
    0.74
     prowess
    0.74
     seriousness
    0.71
     solidarity
    0.68
     commitment
    0.68
     superiority
    0.68
     true
    0.67
     versatility
    0.66
     maturity
    0.65
     importance
    0.65
    Act Density 0.444%

    No Known Activations