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

    Neuronpedia

    INDEX
    Explanations

    statistical data or percentages in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proportions or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agate
    -0.86
     locality
    -0.74
     messenger
    -0.70
    illary
    -0.68
    Trend
    -0.68
    ieu
    -0.67
    upon
    -0.65
    intent
    -0.65
    ocratic
    -0.64
     Globe
    -0.64
    POSITIVE LOGITS
    acebook
    0.70
    arser
    0.70
    agascar
    0.68
    ensibly
    0.66
    inguished
    0.65
    theless
    0.65
    eteen
    0.64
    irds
    0.64
    ecided
    0.62
    irteen
    0.62
    Act Density 0.005%

    No Known Activations