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

    Neuronpedia

    INDEX
    Explanations

    references to specific items or topics explicitly marked with demonstrative pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adius
    -0.18
    mans
    -0.15
     Haz
    -0.15
     lev
    -0.14
    elpers
    -0.14
     free
    -0.14
     rel
    -0.14
     spit
    -0.14
     ham
    -0.13
     Aster
    -0.13
    POSITIVE LOGITS
    enha
    0.18
    .GroupLayout
    0.16
     happened
    0.15
    BorderStyle
    0.15
    issen
    0.15
    Latch
    0.15
    raig
    0.14
    yre
    0.14
    logic
    0.14
    OOSE
    0.14
    Act Density 0.117%

    No Known Activations