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

    Neuronpedia

    INDEX
    Explanations

    entities or concepts often associated with power dynamics and influence

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to entrapment or entanglement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Responsibility
    -0.74
    Games
    -0.68
    Universal
    -0.65
    pmwiki
    -0.63
    TPPStreamerBot
    -0.63
    Ô
    -0.62
    ãĥ£
    -0.62
     Goth
    -0.61
    Beer
    -0.60
    Jump
    -0.59
    POSITIVE LOGITS
    ourage
    1.03
    ailed
    1.02
    ailing
    0.92
    rench
    0.92
    renched
    0.91
    uring
    0.91
    iring
    0.90
    inence
    0.90
    repre
    0.88
    rained
    0.88
    Act Density 0.018%

    No Known Activations