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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Monster"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Monster" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atory
    -1.04
    atories
    -0.95
    ulation
    -0.81
    rive
    -0.80
    ular
    -0.80
    lest
    -0.78
    ulating
    -0.76
    ulatory
    -0.75
    ATED
    -0.75
    pired
    -0.74
    POSITIVE LOGITS
     Parenthood
    0.82
     Hunter
    0.81
     Girl
    0.79
    wagen
    0.79
     Fighters
    0.78
     Energy
    0.74
     Bever
    0.73
     Squad
    0.73
     Caller
    0.72
     Truck
    0.72
    Act Density 0.020%

    No Known Activations