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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the consequences or effects of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iens
    -0.17
    گرÛĮ
    -0.16
    TestFixture
    -0.15
    pNet
    -0.15
    .gdx
    -0.15
    celik
    -0.15
     tinder
    -0.15
    ÑģÑĤÑĢа
    -0.14
    .newBuilder
    -0.14
    dre
    -0.14
    POSITIVE LOGITS
    forth
    0.17
     Bod
    0.16
    em
    0.16
    angen
    0.15
    occo
    0.15
    lias
    0.14
    avir
    0.14
    oco
    0.14
    ieg
    0.13
     apost
    0.13
    Act Density 0.063%

    No Known Activations