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

    Neuronpedia

    INDEX
    Explanations

    mentions of other people or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "others."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Accessory
    -0.74
     centerpiece
    -0.64
    itation
    -0.63
     Herald
    -0.60
     Hulk
    -0.60
    ihara
    -0.59
     Parenthood
    -0.57
    owship
    -0.57
    obar
    -0.57
     Warlock
    -0.57
    POSITIVE LOGITS
    cius
    1.00
    paces
    0.92
    ourcing
    0.81
    ystem
    0.80
    heet
    0.79
    ensitive
    0.78
     who
    0.77
    cript
    0.76
    ngth
    0.73
    hooting
    0.72
    Act Density 0.034%

    No Known Activations