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

    Neuronpedia

    INDEX
    Explanations

    parenthetical expressions or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.60
    Abit
    -0.49
    side
    -0.47
     Hayley
    -0.46
    AnimationsModule
    -0.46
    Portale
    -0.45
     side
    -0.43
     dated
    -0.42
     adv
    -0.41
    adv
    -0.41
    POSITIVE LOGITS
     CD
    1.49
     SD
    1.40
     FD
    1.39
     PD
    1.39
    CD
    1.35
     BD
    1.35
     GD
    1.33
     TD
    1.28
     cd
    1.27
    GD
    1.25
    Act Density 0.600%

    No Known Activations