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

    Neuronpedia

    INDEX
    Explanations

    specific domain-related keywords and web addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.20
    -0.20
     "
    -0.18
     in
    -0.17
     object
    -0.17
     regular
    -0.16
    :
    -0.16
    sian
    -0.16
     and
    -0.16
    Âł
    -0.15
    POSITIVE LOGITS
    onth
    0.22
    que
    0.22
    fort
    0.21
    inth
    0.21
    andin
    0.21
    after
    0.21
    uk
    0.20
    fre
    0.20
    athan
    0.19
    forall
    0.19
    Act Density 0.200%

    No Known Activations