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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or similarity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating consistency or similarity across statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighters
    -0.75
    æĪ¦
    -0.67
     THEN
    -0.65
    orthy
    -0.65
     charcoal
    -0.64
    leased
    -0.63
    ffff
    -0.63
    whe
    -0.60
     INCLUD
    -0.59
     bang
    -0.59
    POSITIVE LOGITS
    pmwiki
    0.87
     everywhere
    0.70
    rences
    0.69
    Shape
    0.65
     Qué
    0.64
     guiActive
    0.63
    lihood
    0.63
     practise
    0.62
     prev
    0.62
     precedent
    0.62
    Act Density 0.435%

    No Known Activations