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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating additional points, issues, or considerations in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amoto
    -0.15
    jumbotron
    -0.15
    å©
    -0.14
    maz
    -0.14
     himself
    -0.14
    ugo
    -0.14
    Ùħد
    -0.13
    mazon
    -0.13
    à¸Ļาย
    -0.13
    marca
    -0.13
    POSITIVE LOGITS
     thin
    0.16
    anny
    0.15
     Wil
    0.15
     Marsh
    0.15
     merits
    0.14
     another
    0.14
    ialized
    0.14
     Klo
    0.14
     Sylv
    0.14
     nữa
    0.14
    Act Density 0.076%

    No Known Activations