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

    Neuronpedia

    INDEX
    Explanations

    expressions of boasting or promoting achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĦÙĪد
    -0.15
     Forces
    -0.15
    yll
    -0.14
    /Sub
    -0.14
     Hour
    -0.14
     Yi
    -0.14
    gro
    -0.14
     forces
    -0.14
     fuer
    -0.14
    stitial
    -0.14
    POSITIVE LOGITS
    ouses
    0.16
    alem
    0.15
    виÑĩ
    0.14
    оÑĢод
    0.14
    umba
    0.14
    wins
    0.14
    åºĨ
    0.14
    abras
    0.14
    .safe
    0.14
    upo
    0.14
    Act Density 0.150%

    No Known Activations