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

    Neuronpedia

    INDEX
    Explanations

    boolean indicators of truthfulness or validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esz
    -0.17
    ickey
    -0.14
    cosa
    -0.14
    omu
    -0.14
    ÏĨα
    -0.14
    cape
    -0.14
    hn
    -0.14
    uur
    -0.14
     Moran
    -0.13
    achts
    -0.13
    POSITIVE LOGITS
    asio
    0.14
    clide
    0.14
    _auc
    0.14
     MES
    0.14
    ewood
    0.14
     Struct
    0.13
    ocate
    0.13
    ίνα
    0.13
     SY
    0.13
    ennes
    0.13
    Act Density 0.039%

    No Known Activations