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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific phrases regarding terms and conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spm
    -0.15
     rad
    -0.14
    aux
    -0.14
    fts
    -0.14
    ohn
    -0.14
     /
    -0.14
    lip
    -0.13
     sert
    -0.13
    529
    -0.13
    .Selenium
    -0.13
    POSITIVE LOGITS
    OffsetTable
    0.17
    antha
    0.15
    -chief
    0.15
    ré
    0.14
    rop
    0.14
     hoá
    0.14
    @nate
    0.14
     collegiate
    0.14
    roupe
    0.14
    hap
    0.14
    Act Density 0.009%

    No Known Activations