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

    Neuronpedia

    INDEX
    Explanations

    specific situations or events described as scenarios

    oai_token-act-pair · gpt-3.5-turbo

    references to hypothetical situations or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enfranch
    -0.80
    anguages
    -0.80
    alties
    -0.78
    ighters
    -0.78
    obe
    -0.76
    igion
    -0.74
    olulu
    -0.74
    ixed
    -0.74
    artney
    -0.74
    emouth
    -0.74
    POSITIVE LOGITS
     scenarios
    0.95
     scenario
    0.94
     involving
    0.78
    eers
    0.77
     unfold
    0.72
     2030
    0.71
     unfolding
    0.71
    ttes
    0.65
     2100
    0.65
     Situation
    0.64
    Act Density 0.020%

    No Known Activations