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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate authorship or sources of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fighters
    -0.17
    кÑĢеÑĤ
    -0.17
    KeySpec
    -0.17
    CLUDING
    -0.16
    ATUS
    -0.15
    ibrator
    -0.15
    ViewById
    -0.15
    abay
    -0.14
    uent
    -0.14
    ucha
    -0.14
    POSITIVE LOGITS
     means
    0.28
     virtue
    0.24
     dint
    0.21
     team
    0.17
    means
    0.17
    -products
    0.16
     mistake
    0.16
     authorities
    0.16
     teams
    0.16
     analogy
    0.16
    Act Density 0.190%

    No Known Activations