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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to products or services being offered

    oai_token-act-pair · gpt-3.5-turbo

    offer-related terms indicating services or solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sis
    -0.78
    pac
    -0.68
    cling
    -0.65
    arson
    -0.65
    osate
    -0.64
    tar
    -0.62
    avia
    -0.62
     habit
    -0.60
    cles
    -0.59
    san
    -0.59
    POSITIVE LOGITS
     refunds
    0.84
     discounts
    0.80
     condolences
    0.76
    xual
    0.74
     offerings
    0.72
    ises
    0.69
     promotions
    0.69
    jri
    0.68
    iders
    0.68
    Allows
    0.67
    Act Density 0.039%

    No Known Activations