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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe specific moments in time or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    encers
    -0.83
    inals
    -0.74
    upon
    -0.72
    ifax
    -0.71
    ocate
    -0.70
    avorite
    -0.70
     sucks
    -0.69
    RIC
    -0.66
    blers
    -0.66
    encer
    -0.65
    POSITIVE LOGITS
     occasions
    1.12
     behalf
    1.00
     heels
    0.98
     basis
    0.95
     pedest
    0.95
     eve
    0.92
     occasion
    0.91
     periphery
    0.90
     rooft
    0.88
     doorstep
    0.87
    Act Density 0.616%

    No Known Activations