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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of selection or collection

    oai_token-act-pair · gpt-3.5-turbo

    words related to selection and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPS
    -0.67
    ordes
    -0.67
    bie
    -0.66
     Redemption
    -0.62
    corn
    -0.62
     Sharon
    -0.61
    Reward
    -0.61
    swick
    -0.59
    HQ
    -0.59
    HA
    -0.58
    POSITIVE LOGITS
    eor
    0.95
    inel
    0.94
    acular
    0.88
    ezvous
    0.87
    ivities
    0.85
    llor
    0.81
    azines
    0.81
    glass
    0.79
    pick
    0.79
    oral
    0.78
    Act Density 0.063%

    No Known Activations