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

    Neuronpedia

    INDEX
    Explanations

    references to a first or second time occurrence

    oai_token-act-pair · gpt-3.5-turbo

    references to the first or second occurrence of events or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çī
    -0.67
    iano
    -0.65
     pione
    -0.65
    sleep
    -0.62
    apons
    -0.62
    lua
    -0.60
     subur
    -0.60
    hunter
    -0.59
     volunte
    -0.58
    stro
    -0.58
    POSITIVE LOGITS
     culmination
    0.74
     anniversary
    0.67
     uproar
    0.66
     downfall
    0.65
     fraught
    0.64
     contention
    0.64
     installment
    0.63
     awaited
    0.63
     understatement
    0.63
     bitters
    0.63
    Act Density 0.175%

    No Known Activations