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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing or presenting options or benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.76
    sis
    -0.73
    pac
    -0.69
    cles
    -0.68
    cling
    -0.67
    osate
    -0.65
    cus
    -0.65
    alde
    -0.63
    prints
    -0.63
    athan
    -0.63
    POSITIVE LOGITS
     condolences
    0.81
     discounts
    0.80
     insight
    0.79
     refunds
    0.78
    xual
    0.77
     alternatives
    0.72
     us
    0.71
    orld
    0.70
     unparalleled
    0.69
    iders
    0.69
    Act Density 0.028%

    No Known Activations