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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to system errors and signals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.67
    in
    -0.62
    2
    -0.61
     on
    -0.60
    .
    -0.59
    1
    -0.58
    6
    -0.58
     (
    -0.58
     of
    -0.58
     in
    -0.58
    POSITIVE LOGITS
     kasarigan
    1.21
     Efq
    1.18
     houſe
    1.11
    ſelves
    1.08
     Houſe
    1.05
     Majefty
    1.02
    ſelf
    1.02
    UserScript
    1.01
     ſmall
    1.00
     مرئيه
    1.00
    Act Density 0.371%

    No Known Activations