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

    Neuronpedia

    INDEX
    Explanations

    references to long-form content or the concept of lengthy communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    548
    -0.16
    æľĭ
    -0.15
     Marty
    -0.14
     universal
    -0.14
    bare
    -0.14
     Stall
    -0.14
    ye
    -0.14
     larg
    -0.14
     ma
    -0.14
     hyper
    -0.14
    POSITIVE LOGITS
     semiclass
    0.16
    uce
    0.15
     èIJ
    0.15
    avad
    0.14
    sett
    0.14
     dÃłi
    0.14
    apsed
    0.13
    .term
    0.13
    obsolete
    0.13
    eneric
    0.13
    Act Density 0.138%

    No Known Activations