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

    Neuronpedia

    INDEX
    Explanations

    assertions about beliefs and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     isn
    -1.10
     aren
    -1.10
     weren
    -1.04
     shouldn
    -1.04
     hasn
    -0.99
    doesn
    -0.99
     wasn
    -0.98
    Couldn
    -0.96
     Doesn
    -0.96
     doesn
    -0.96
    POSITIVE LOGITS
     cannot
    0.75
    cannot
    0.71
    Cannot
    0.68
     Cannot
    0.65
    Tetapi
    0.50
    principalTable
    0.47
     tidak
    0.46
     did
    0.46
     tetapi
    0.43
    但是
    0.42
    Act Density 0.369%

    No Known Activations