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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal terminology and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens appearing next to mathematical symbols/variables

    np_acts-logits-general · gemini-2.0-flash

    reverse chronological

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Theſe
    -1.56
     myſelf
    -1.50
     Monfieur
    -1.49
     houſe
    -1.43
     pleaſure
    -1.37
     Efq
    -1.36
    ſelf
    -1.36
     Jefus
    -1.33
     Houſe
    -1.31
     purpoſe
    -1.31
    POSITIVE LOGITS
     T
    0.72
     
    0.67
     U
    0.65
    ↵
    0.64
     C
    0.64
     di
    0.63
     l
    0.62
     W
    0.62
    <eos>
    0.61
     B
    0.60
    Act Density 1.959%

    No Known Activations