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

    Neuronpedia

    INDEX
    Explanations

    references to research institutions and grant information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amework
    -0.17
    owler
    -0.16
    iture
    -0.15
    æ
    -0.15
    aler
    -0.15
     GOODMAN
    -0.14
    ãĥĥãĥĪ
    -0.14
    alus
    -0.14
    qw
    -0.13
    太éĥİ
    -0.13
    POSITIVE LOGITS
     Ment
    0.21
     ment
    0.20
     career
    0.18
     mechanism
    0.18
    career
    0.18
     Brass
    0.18
     Career
    0.18
    tram
    0.17
     aw
    0.17
     Minority
    0.17
    Act Density 0.008%

    No Known Activations