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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant risks and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rias
    -0.16
     ÙħÛĮÙĦ
    -0.15
    Own
    -0.15
    halt
    -0.15
    uben
    -0.14
    CreatedBy
    -0.14
    regnum
    -0.14
    alez
    -0.14
    aż
    -0.14
    enta
    -0.13
    POSITIVE LOGITS
    enna
    0.15
    ại
    0.15
    opes
    0.15
    anni
    0.15
    Av
    0.14
    ope
    0.14
    .opens
    0.13
    ç¬ij
    0.13
     av
    0.13
     Av
    0.13
    Act Density 1.322%

    No Known Activations