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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or stipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ichel
    -0.16
     Walsh
    -0.15
    uder
    -0.15
     va
    -0.15
     Aber
    -0.15
    acz
    -0.15
    iren
    -0.15
    ianne
    -0.14
    902
    -0.14
    ais
    -0.14
    POSITIVE LOGITS
    rawler
    0.16
    radu
    0.15
    canf
    0.15
    ãĤ§
    0.15
    .decorate
    0.14
    ystack
    0.14
    aktu
    0.14
    uti
    0.14
    ojÃŃ
    0.14
    ÃĹ↵↵
    0.14
    Act Density 0.138%

    No Known Activations