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

    Neuronpedia

    INDEX
    Explanations

    words containing special characters like ÂŃ

    oai_token-act-pair · gpt-3.5-turbo

    indications of large quantities or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intimidated
    -0.63
     Nebula
    -0.61
    DragonMagazine
    -0.60
     Spice
    -0.60
    ilts
    -0.60
     Skull
    -0.60
     remake
    -0.59
    engeance
    -0.58
     Hats
    -0.58
     Kore
    -0.57
    POSITIVE LOGITS
    ships
    0.81
    selves
    0.81
    ship
    0.78
    tal
    0.77
    la
    0.75
    nesota
    0.73
    city
    0.72
    Ñı
    0.71
    late
    0.69
    tion
    0.69
    Act Density 0.018%

    No Known Activations