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

    Neuronpedia

    INDEX
    Explanations

    phrases related to small or insignificant details

    oai_token-act-pair · gpt-3.5-turbo

    mentions of small entities or concepts that emphasize importance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Skies
    -0.79
    åĭ
    -0.69
     Roses
    -0.67
    andise
    -0.67
    hibited
    -0.66
    ukong
    -0.65
    ayn
    -0.65
     Gleaming
    -0.63
    aundering
    -0.60
    metics
    -0.58
    POSITIVE LOGITS
     (<
    1.32
     (~
    0.83
     insignificant
    0.82
     scattered
    0.80
    tiny
    0.80
     sized
    0.80
     niche
    0.79
     incremental
    0.78
     increments
    0.75
    Enlarge
    0.74
    Act Density 0.358%

    No Known Activations