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

    Neuronpedia

    INDEX
    Explanations

    words ending with the suffix "ed"

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.91
    å£
    -0.71
    FTWARE
    -0.70
    fruit
    -0.65
    SPONSORED
    -0.65
    Story
    -0.64
    ãĥĺ
    -0.63
    ersive
    -0.61
    asca
    -0.61
    ãģį
    -0.60
    POSITIVE LOGITS
    uct
    1.12
    ict
    1.06
    dit
    1.02
    rill
    0.93
    ication
    0.93
    aily
    0.92
    nesday
    0.91
    icts
    0.91
    ipal
    0.89
    ges
    0.89
    Act Density 0.039%

    No Known Activations