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

    Neuronpedia

    INDEX
    Explanations

    words related to inactivity or lack of action

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inactivity or idleness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.87
    icz
    -0.86
    alez
    -0.83
    imet
    -0.80
    ulkan
    -0.80
    obal
    -0.79
    obar
    -0.78
     Devi
    -0.75
    oho
    -0.75
    coni
    -0.73
    POSITIVE LOGITS
     idle
    1.17
     Idle
    0.91
     chatter
    0.88
    bank
    0.67
     standby
    0.67
     timer
    0.66
    holders
    0.65
     timers
    0.63
    lings
    0.63
    bum
    0.63
    Act Density 0.008%

    No Known Activations