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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of collaborative processes or group dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fad
    -0.21
    clist
    -0.15
     downright
    -0.15
    rique
    -0.14
    öh
    -0.14
    á»Ļt
    -0.13
    ardon
    -0.13
     nich
    -0.13
    UNUSED
    -0.13
    ย
    -0.13
    POSITIVE LOGITS
     inhab
    0.18
    ãĥ³ãĥĸ
    0.17
     vé
    0.17
     dna
    0.16
    uteur
    0.16
     sort
    0.16
    tems
    0.16
    stakes
    0.16
     Olivier
    0.16
     filmmakers
    0.16
    Act Density 0.065%

    No Known Activations