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

    Neuronpedia

    INDEX
    Explanations

    references to transactions or business practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .?
    -0.98
    *.
    -0.87
    '.
    -0.81
    .</
    -0.79
    %.
    -0.77
    `.
    -0.77
    $.
    -0.74
    .''.
    -0.74
    "!
    -0.71
    .
    -0.71
    POSITIVE LOGITS
     however
    0.96
     though
    0.79
     meanwhile
    0.65
     but
    0.58
     tho
    0.56
     pickups
    0.52
     Ogre
    0.49
     veter
    0.47
     grunt
    0.46
    ecause
    0.46
    Act Density 11.960%

    No Known Activations