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

    Neuronpedia

    INDEX
    Explanations

    references to job opportunities and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.85
     morrow
    -0.83
     ſeveral
    -0.83
     ſtate
    -0.82
     houſe
    -0.81
     Assyrian
    -0.80
     ftate
    -0.79
     fevere
    -0.75
     Babylonian
    -0.75
     itſelf
    -0.74
    POSITIVE LOGITS
     knew
    0.63
     was
    0.56
     did
    0.55
     صوتيه
    0.55
     didn
    0.54
    UnsafeEnabled
    0.53
     Knew
    0.52
     wasn
    0.52
     hadn
    0.51
     led
    0.49
    Act Density 0.371%

    No Known Activations