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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating the cessation or continuation of action

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating persistence or determination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocr
    -0.69
    sonian
    -0.67
    ighth
    -0.65
    oran
    -0.62
    ummer
    -0.61
    soDeliveryDate
    -0.60
    pert
    -0.60
    otation
    -0.59
    solete
    -0.57
    axter
    -0.57
    POSITIVE LOGITS
     anymore
    0.98
     nor
    0.96
     either
    0.75
     temptation
    0.70
     whatsoever
    0.69
    !:
    0.61
    ZE
    0.59
    til
    0.59
    gor
    0.57
     grinning
    0.57
    Act Density 0.132%

    No Known Activations