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

    Neuronpedia

    INDEX
    Explanations

    statements that express clarity or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    didSet
    -0.76
    ofollow
    -0.66
     arXiv
    -0.65
     AssemblyTitle
    -0.65
    octo
    -0.63
    Życiorys
    -0.63
    Према
    -0.62
    OrNil
    -0.60
     XMLHttpRequest
    -0.60
    脚注の使い方
    -0.60
    POSITIVE LOGITS
     clearly
    0.98
     clear
    0.90
     spectacular
    0.85
     prominent
    0.80
     dramatically
    0.80
    clearly
    0.73
     isolated
    0.70
     obvious
    0.70
     dramatic
    0.70
     vivid
    0.66
    Act Density 0.104%

    No Known Activations