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

    Neuronpedia

    INDEX
    Explanations

    situations where something positive or beneficial happens due to a specific action or reason

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atform
    -0.73
    女
    -0.72
     Ukrain
    -0.64
     Scotia
    -0.63
    estern
    -0.60
    FO
    -0.60
    ILLE
    -0.59
    ISH
    -0.57
    åĬ
    -0.57
     Rebell
    -0.57
    POSITIVE LOGITS
    giving
    1.35
    ration
    0.83
    ĸļ
    0.78
    gers
    0.76
    gewater
    0.74
    ESCO
    0.73
    graded
    0.71
    brance
    0.68
    roxy
    0.66
    kowski
    0.66
    Act Density 0.016%

    No Known Activations