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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to environmental hazards or concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }.
    -0.70
    ]."
    -0.70
    )."
    -0.70
    )).
    -0.65
    !).
    -0.62
     therein
    -0.61
    ]).
    -0.57
     ende
    -0.56
    >.
    -0.56
    %).
    -0.54
    POSITIVE LOGITS
     âĵĺ
    0.62
    iens
    0.55
     celebrates
    0.54
     consists
    0.53
     extends
    0.52
     greets
    0.52
     collided
    0.51
     Association
    0.51
     reacts
    0.50
     proposes
    0.49
    Act Density 0.803%

    No Known Activations