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

    Neuronpedia

    INDEX
    Explanations

    references to sharing content on social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.80
    erity
    -0.70
    */(
    -0.69
     WATCHED
    -0.68
    ��
    -0.67
    INGS
    -0.66
    ALE
    -0.63
     paraph
    -0.62
     tremend
    -0.62
    MpServer
    -0.62
    POSITIVE LOGITS
    plate
    0.75
    Prev
    0.69
     Arrow
    0.68
    plates
    0.65
    heat
    0.64
     Sina
    0.62
    beam
    0.58
    kin
    0.58
    utm
    0.58
    ranch
    0.57
    Act Density 0.027%

    No Known Activations