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

    Neuronpedia

    INDEX
    Explanations

    concepts related to respect and its various manifestations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.17
    ÑģÑĤва
    -0.17
    issance
    -0.15
    presso
    -0.15
    erals
    -0.15
    rys
    -0.15
    icine
    -0.15
    ux
    -0.15
    elim
    -0.14
    kits
    -0.14
    POSITIVE LOGITS
    ively
    0.40
    ably
    0.31
    ability
    0.26
    ually
    0.22
    ors
    0.22
    uously
    0.21
    ully
    0.20
    uous
    0.19
    able
    0.18
    ible
    0.17
    Act Density 0.031%

    No Known Activations