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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating progression or advancement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progression or advancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odor
    -0.66
    CLUD
    -0.62
    gencies
    -0.62
     Intake
    -0.62
    clud
    -0.60
    ricted
    -0.59
    ellar
    -0.58
    entary
    -0.57
     Cth
    -0.56
     constant
    -0.54
    POSITIVE LOGITS
     by
    0.94
     lately
    0.74
    :
    0.74
     when
    0.73
     with
    0.71
     whereby
    0.69
     here
    0.68
     introducing
    0.68
     courtesy
    0.67
     Dragonbound
    0.66
    Act Density 0.323%

    No Known Activations