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

    Neuronpedia

    INDEX
    Explanations

    terms related to absence or lack of measured effects in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.72
     dieß
    -0.66
     whoſe
    -0.65
     Reſ
    -0.59
    Matter
    -0.57
     Allez
    -0.57
     ſeveral
    -0.56
     Theſe
    -0.56
     houſe
    -0.56
     Jefus
    -0.55
    POSITIVE LOGITS
     CreateTagHelper
    0.63
    basicConfig
    0.59
     melainkan
    0.48
    Према
    0.47
     nor
    0.47
    text
    0.47
     vueltas
    0.47
     except
    0.46
     ddelweddau
    0.45
    stress
    0.45
    Act Density 0.830%

    No Known Activations