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

    Neuronpedia

    INDEX
    Explanations

    terms related to evidence or validation of claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /small
    -0.15
    /or
    -0.15
    uri
    -0.14
    INET
    -0.14
    umin
    -0.14
    quate
    -0.14
    upon
    -0.14
     Westbrook
    -0.14
    prises
    -0.14
    grund
    -0.14
    POSITIVE LOGITS
    룹
    0.16
    eed
    0.14
    ably
    0.14
     latina
    0.14
    atively
    0.14
    ando
    0.14
    ısından
    0.14
    /Test
    0.14
    ollar
    0.14
    /test
    0.14
    Act Density 0.048%

    No Known Activations