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

    Neuronpedia

    INDEX
    Explanations

    non-zero values of "Ļ"

    oai_token-act-pair · gpt-3.5-turbo

    instances of a particular character or symbol in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undown
    -0.81
     Palestin
    -0.72
     carbohyd
    -0.69
     Wilmington
    -0.68
     tides
    -0.68
    ickets
    -0.66
     disadvant
    -0.65
     paperback
    -0.64
    ierrez
    -0.64
     fortun
    -0.63
    POSITIVE LOGITS
    ï¸ı
    0.98
    agree
    0.82
    legal
    0.75
    é¾į
    0.72
    kay
    0.72
    mir
    0.72
    mand
    0.71
     personally
    0.70
    glass
    0.70
     myself
    0.69
    Act Density 0.139%

    No Known Activations