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

    Neuronpedia

    INDEX
    Explanations

    mentions of potential or hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulu
    -0.91
    cipline
    -0.87
    strap
    -0.85
    region
    -0.82
    kai
    -0.81
    ients
    -0.80
    mson
    -0.80
    gar
    -0.80
    lite
    -0.80
    ient
    -0.78
    POSITIVE LOGITS
     future
    0.92
     successors
    0.87
     fallout
    0.85
     obstruction
    0.84
     defect
    0.83
     inclusion
    0.82
     culprit
    0.82
     hazards
    0.82
     embodiments
    0.81
     solutions
    0.81
    Act Density 0.042%

    No Known Activations