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

    Neuronpedia

    INDEX
    Explanations

    actions or events related to specific activities or tasks being performed by characters

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to gameplay and character interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tone
    -0.75
    rea
    -0.68
    sw
    -0.66
    conn
    -0.66
    eur
    -0.64
    rez
    -0.61
    Bey
    -0.60
    zo
    -0.59
    gran
    -0.59
    seekers
    -0.57
    POSITIVE LOGITS
    ometimes
    1.20
    omething
    1.04
    hift
    1.01
    paces
    0.94
    hirt
    0.92
    ilver
    0.87
    ettings
    0.83
    hooting
    0.81
    ynthesis
    0.79
    heet
    0.76
    Act Density 0.414%

    No Known Activations