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

    Neuronpedia

    INDEX
    Explanations

    references to scientific authors and their respective contributions in academic publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Slav
    -0.76
     Hoi
    -0.69
    ()?;
    -0.67
     HAST
    -0.67
    VolleyError
    -0.67
    Dank
    -0.66
     bibli
    -0.66
     Spra
    -0.65
     Pret
    -0.65
     Clap
    -0.64
    POSITIVE LOGITS
     K
    1.24
     H
    1.15
     O
    1.15
     M
    1.13
     C
    1.08
     S
    1.07
     D
    1.06
     B
    1.03
     F
    1.03
     W
    1.02
    Act Density 1.667%

    No Known Activations