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

    Neuronpedia

    INDEX
    Explanations

    phrases related to struggles or difficult experiences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and phrases that indicate continuation or elaboration in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¥
    -0.70
    TN
    -0.70
    leground
    -0.68
    boro
    -0.68
    arov
    -0.66
    etary
    -0.64
    eal
    -0.64
    ril
    -0.64
    raq
    -0.63
    eed
    -0.63
    POSITIVE LOGITS
     somew
    0.97
     however
    0.85
     though
    0.71
     nobody
    0.63
     alas
    0.63
    SPONSORED
    0.61
     determining
    0.61
     neither
    0.61
     minimizing
    0.59
     adop
    0.59
    Act Density 0.291%

    No Known Activations