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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decision-making and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Belg
    -0.71
     Klux
    -0.65
    bestos
    -0.64
    bern
    -0.64
     Paragu
    -0.63
    outhern
    -0.62
    culosis
    -0.62
     Buckley
    -0.61
    arij
    -0.60
     communists
    -0.60
    POSITIVE LOGITS
     accordingly
    0.97
     interact
    0.80
     patterns
    0.80
     tasks
    0.79
     facets
    0.78
     behaviours
    0.78
     feedback
    0.77
     motions
    0.77
     timelines
    0.75
     cues
    0.74
    Act Density 1.042%

    No Known Activations