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

    Neuronpedia

    INDEX
    Explanations

    discussions about car safety ratings and crash test results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    ãĥ¼ãĥ³
    -0.16
    orda
    -0.15
    perms
    -0.15
    braco
    -0.14
    icus
    -0.14
    dra
    -0.14
    _PKT
    -0.14
    .decorate
    -0.14
    adata
    -0.14
    POSITIVE LOGITS
    enheim
    0.15
     Gur
    0.15
    avern
    0.14
     err
    0.14
    engu
    0.14
    mae
    0.14
     Err
    0.14
    iger
    0.14
    etti
    0.13
    arella
    0.13
    Act Density 0.013%

    No Known Activations