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

    Neuronpedia

    INDEX
    Explanations

    names, dates, and duration mentions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     demag
    -0.52
    Zul
    -0.49
    Vind
    -0.49
     induct
    -0.47
    businessman
    -0.47
     caprice
    -0.46
     sophistic
    -0.46
    TheReal
    -0.46
     vexed
    -0.46
     Havel
    -0.45
    POSITIVE LOGITS
    tagena
    0.75
    membrance
    0.74
     bandung
    0.71
     sappi
    0.69
     incess
    0.68
     credere
    0.68
     torner
    0.67
     parteci
    0.67
     prega
    0.67
     domani
    0.65
    Act Density 0.119%

    No Known Activations