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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate specific organizational or classification structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.20
     ro
    -0.19
     (
    -0.17
     eh
    -0.17
    -
    -0.16
    /
    -0.16
     /
    -0.16
     pret
    -0.16
     :
    -0.16
     powered
    -0.16
    POSITIVE LOGITS
    achen
    0.17
    pie
    0.17
    ailable
    0.17
    Markup
    0.16
    /groups
    0.16
    assen
    0.16
    nton
    0.15
     лиÑĨ
    0.15
    atsapp
    0.15
    бÑĥ
    0.15
    Act Density 0.041%

    No Known Activations