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

    Neuronpedia

    INDEX
    Explanations

    YouTube video links

    oai_token-act-pair · gpt-3.5-turbo

    video identifiers and links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mushrooms
    -0.66
     battered
    -0.62
     specialists
    -0.62
     Lovecraft
    -0.60
     bis
    -0.59
     womb
    -0.59
     rallies
    -0.59
     apolog
    -0.59
     signs
    -0.58
     wonders
    -0.58
    POSITIVE LOGITS
    =
    1.49
    =-
    1.24
    =$
    1.18
    =/
    1.16
    =[
    1.08
    ={
    1.02
    =\"
    0.96
    ='
    0.95
    =#
    0.92
    =(
    0.90
    Act Density 0.047%

    No Known Activations