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

    Neuronpedia

    INDEX
    Explanations

    YouTube video references

    oai_token-act-pair · gpt-3.5-turbo

    elements related to video content and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     battered
    -0.72
     arsen
    -0.70
     signs
    -0.70
     mushrooms
    -0.69
     imperson
    -0.67
     shocks
    -0.66
     pars
    -0.65
     derog
    -0.65
     recovers
    -0.64
     apolog
    -0.63
    POSITIVE LOGITS
    =
    1.81
    =-
    1.51
    =/
    1.48
    =$
    1.47
    =[
    1.41
    ={
    1.39
    ='
    1.33
    =(
    1.19
    =\"
    1.18
    ="
    1.17
    Act Density 0.037%

    No Known Activations