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

    Neuronpedia

    INDEX
    Explanations

    adjectives that convey strong emotional or qualitative attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Teams
    -0.21
     Teams
    -0.20
     Groups
    -0.19
    Groups
    -0.19
     Families
    -0.19
     Colleges
    -0.18
     Committees
    -0.18
     Schools
    -0.17
     Boards
    -0.17
     Churches
    -0.17
    POSITIVE LOGITS
     themselves
    0.34
     substitutes
    0.30
     additions
    0.30
     placeholders
    0.28
     ones
    0.27
     replacements
    0.27
     staples
    0.27
     predictors
    0.26
     indicators
    0.26
     contributors
    0.26
    Act Density 0.247%

    No Known Activations