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

    Neuronpedia

    INDEX
    Explanations

    words with Finnish accents or characters

    oai_token-act-pair · gpt-3.5-turbo

    tokens representing specific measurements or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bubble
    -0.70
     hosting
    -0.62
     surrogate
    -0.62
     bidding
    -0.60
     poster
    -0.60
     Gates
    -0.59
     microbi
    -0.59
     Mouth
    -0.58
     Disaster
    -0.57
     WOR
    -0.56
    POSITIVE LOGITS
    lt
    4.38
    gt
    1.79
    lv
    1.55
    lf
    1.49
    ls
    1.41
    rt
    1.31
    mt
    1.29
    lam
    1.25
    ld
    1.23
    ln
    1.17
    Act Density 0.012%

    No Known Activations