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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their significance in a legal or contractual context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.92
     Archa
    -0.83
     itſelf
    -0.83
     perfons
    -0.81
     masts
    -0.80
     raiſ
    -0.79
     juſt
    -0.78
     myſelf
    -0.76
     himſelf
    -0.75
    ſelves
    -0.74
    POSITIVE LOGITS
    Personensuche
    0.56
     “
    0.54
    autoconfigure
    0.53
    DebuggerNonUser
    0.52
    ORMAL
    0.51
     so
    0.51
    AutoScaleMode
    0.50
     Heart
    0.48
     >=",
    0.48
     near
    0.48
    Act Density 0.012%

    No Known Activations