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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zos
    -0.84
    sers
    -0.70
     âĶľâĶĢâĶĢ
    -0.65
    yah
    -0.65
     ;;
    -0.65
    vec
    -0.65
     snipp
    -0.62
    atl
    -0.62
     âĹı
    -0.57
    lass
    -0.57
    POSITIVE LOGITS
     respectively
    0.72
     disclaim
    0.66
    emis
    0.63
     Gamble
    0.61
     brow
    0.60
    iffe
    0.60
     Mann
    0.58
     breast
    0.56
     prisons
    0.56
     Dug
    0.56
    Act Density 0.247%

    No Known Activations