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

    Neuronpedia

    INDEX
    Explanations

    instances where a person leaves a particular situation or place

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or events that occur after a specific point in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.74
    ocy
    -0.71
    âĨij
    -0.68
    ouse
    -0.67
    =-=-=-=-=-=-=-=-
    -0.66
    bered
    -0.66
    uckland
    -0.65
    oya
    -0.64
    Enabled
    -0.63
    IZE
    -0.62
    POSITIVE LOGITS
     completing
    1.18
     serving
    1.07
     spending
    1.07
     defeating
    1.07
     enduring
    1.05
     years
    1.04
     decades
    1.03
     undergoing
    1.02
     graduating
    1.01
     months
    1.01
    Act Density 0.095%

    No Known Activations