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

    Neuronpedia

    INDEX
    Explanations

    references to topics of discussion or subjects being talked about

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    i
    -0.63
    ral
    -0.61
     Nw
    -0.60
     D
    -0.60
     russes
    -0.60
     Hua
    -0.60
    ा
    -0.59
    Full
    -0.58
     alve
    -0.57
     Barra
    -0.57
    POSITIVE LOGITS
     about
    1.47
     ABOUT
    1.47
     abt
    1.45
    ABOUT
    1.40
    Bout
    1.32
    bout
    1.31
     About
    1.30
     Bout
    1.29
    About
    1.20
    antMatchers
    1.20
    Act Density 0.128%

    No Known Activations