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

    Neuronpedia

    INDEX
    Explanations

    sentences or clauses that contain numerical values or punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.15
    alist
    -0.15
    ding
    -0.15
    esan
    -0.15
     support
    -0.15
     tam
    -0.15
    eson
    -0.15
    n
    -0.15
    errat
    -0.14
    uc
    -0.14
    POSITIVE LOGITS
    gether
    0.16
    terminal
    0.16
    oreach
    0.15
    stroy
    0.14
    istrovstvÃŃ
    0.14
     milano
    0.14
    Ùħبر
    0.14
    .Undef
    0.14
    ito
    0.14
    ifestyles
    0.14
    Act Density 0.118%

    No Known Activations