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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "First" indicating the beginning of sections or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTH
    -0.16
    aron
    -0.16
    nip
    -0.15
    agh
    -0.15
    otope
    -0.14
    _hs
    -0.14
     McDon
    -0.14
    ground
    -0.14
    ovich
    -0.14
    ause
    -0.14
    POSITIVE LOGITS
    asyon
    0.16
    azes
    0.15
    illis
    0.15
    #__
    0.14
    orge
    0.14
    ugas
    0.14
    ë¡Ģ
    0.14
    áºł
    0.14
     Tar
    0.14
    quez
    0.14
    Act Density 0.081%

    No Known Activations