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

    Neuronpedia

    INDEX
    Explanations

    whitespace in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DebuggerNonUser
    -0.63
    LikeLike
    -0.53
    jid
    -0.51
     newBuilder
    -0.49
     signal
    -0.49
     विश्वसनीयता
    -0.47
     урна
    -0.46
     Petersen
    -0.46
    tedly
    -0.46
     referrerpolicy
    -0.46
    POSITIVE LOGITS
     Theſe
    0.81
     itſelf
    0.79
     Shakspeare
    0.78
    FDRE
    0.77
     whoſe
    0.74
     Majefty
    0.74
     Efq
    0.73
     ſhould
    0.73
     fhew
    0.72
     Monfieur
    0.70
    Act Density 0.055%

    No Known Activations