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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating isolation or exclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elo
    -0.15
    æļĤ
    -0.15
    åį¢
    -0.15
    umba
    -0.14
    ấp
    -0.14
    Ĺ
    -0.14
     Trials
    -0.14
     swe
    -0.14
    undy
    -0.14
     Popular
    -0.14
    POSITIVE LOGITS
    bris
    0.18
    .CG
    0.15
    URRED
    0.15
    кÑĥÑĢ
    0.15
    _SU
    0.14
     Shapes
    0.14
    ξε
    0.14
    oppins
    0.14
    gart
    0.14
    414
    0.14
    Act Density 0.019%

    No Known Activations