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

    Neuronpedia

    INDEX
    Explanations

    negations using the phrase "let alone"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce conditions or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cumbers
    -0.71
    HAM
    -0.67
    bage
    -0.65
     vending
    -0.61
    lihood
    -0.61
    ource
    -0.60
    Zen
    -0.59
    insula
    -0.57
    aeda
    -0.57
     holiest
    -0.57
    POSITIVE LOGITS
    tered
    0.94
    tering
    0.86
    itia
    0.81
    icia
    0.73
    arations
    0.73
    inous
    0.72
    yrs
    0.72
    ting
    0.71
     us
    0.70
    ÃŃn
    0.70
    Act Density 0.025%

    No Known Activations