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

    Neuronpedia

    INDEX
    Explanations

    references to commercial or business activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thia
    -0.67
    apego
    -0.65
    stals
    -0.64
    ãĥŃ
    -0.62
     Tot
    -0.62
     Shards
    -0.61
     tiss
    -0.61
     Dwell
    -0.59
    adoes
    -0.58
    ados
    -0.58
    POSITIVE LOGITS
     mogul
    1.06
     dealings
    1.00
    woman
    0.88
    manship
    0.85
     interests
    0.84
    mens
    0.83
    women
    0.82
     droid
    0.82
    week
    0.80
    INESS
    0.79
    Act Density 0.025%

    No Known Activations