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

    Neuronpedia

    INDEX
    Explanations

    phrases related to liability and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iyet
    -0.16
    antium
    -0.15
    onga
    -0.15
    ioned
    -0.14
    ante
    -0.14
    ุส
    -0.14
    gia
    -0.14
    engo
    -0.14
    .jquery
    -0.14
    .mov
    -0.14
    POSITIVE LOGITS
    ile
    0.15
     Dorm
    0.15
    BackStack
    0.14
    823
    0.14
    iam
    0.14
    esti
    0.14
     personally
    0.14
    ãĥĹãĥª
    0.14
    agg
    0.14
     Hatch
    0.13
    Act Density 0.003%

    No Known Activations