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

    Neuronpedia

    INDEX
    Explanations

    programming syntax elements and punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rebellion
    -0.18
    oland
    -0.17
     MIS
    -0.14
    uges
    -0.14
     Rage
    -0.14
    ilde
    -0.14
    .wp
    -0.14
    Strike
    -0.14
    zych
    -0.14
     Strike
    -0.13
    POSITIVE LOGITS
     unless
    0.27
    unless
    0.26
     scalar
    0.23
     cro
    0.22
     Scalar
    0.22
     confess
    0.22
    cro
    0.22
     Carp
    0.22
    undef
    0.21
     die
    0.21
    Act Density 0.003%

    No Known Activations