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

    Neuronpedia

    INDEX
    Explanations

    phrases connoting consequential outcomes or results

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "end up"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aic
    -0.65
    Scroll
    -0.62
    apo
    -0.61
    ï¸ı
    -0.60
    TON
    -0.58
    hetics
    -0.57
    heses
    -0.57
    });
    -0.57
    rote
    -0.57
    onnaissance
    -0.57
    POSITIVE LOGITS
     liking
    1.19
     costing
    1.16
     hurting
    1.12
     needing
    1.09
     settling
    1.09
     marrying
    1.07
     paying
    1.07
     hating
    1.05
     deleting
    1.04
     owning
    1.04
    Act Density 0.048%

    No Known Activations