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

    Neuronpedia

    INDEX
    Explanations

    phrases related to having something remaining or not being used up

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of remaining quantity or time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.85
     Mbps
    -0.77
     guid
    -0.71
    wcsstore
    -0.66
     metic
    -0.64
     narc
    -0.63
     blackout
    -0.62
    yrinth
    -0.61
     millisec
    -0.61
     Pengu
    -0.60
    POSITIVE LOGITS
    overs
    0.92
     undone
    0.89
     unexpl
    0.80
     unanswered
    0.74
     Alive
    0.70
     alive
    0.68
    illes
    0.68
    orea
    0.67
    ilage
    0.65
     unused
    0.65
    Act Density 0.045%

    No Known Activations