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

    Neuronpedia

    INDEX
    Explanations

    references to specific sports teams and players

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.62
     in
    -0.93
     no
    -0.93
     to
    -0.92
     at
    -0.89
     for
    -0.89
     so
    -0.88
    .
    -0.88
     as
    -0.86
     on
    -0.85
    POSITIVE LOGITS
     hcm
    2.49
     mef
    2.28
     lele
    2.26
     alkoh
    2.24
     immen
    2.22
     kram
    2.22
     franz
    2.21
     antik
    2.20
     cannes
    2.19
     „,
    2.19
    Act Density 0.610%

    No Known Activations