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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unfolding events or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to events unfolding over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iceps
    -0.68
    clerosis
    -0.68
    IDS
    -0.66
     arrivals
    -0.66
     explorers
    -0.65
    ¿½
    -0.63
     brethren
    -0.63
    expr
    -0.63
     combatants
    -0.62
     shipments
    -0.60
    POSITIVE LOGITS
    arro
    0.78
    cha
    0.68
    anos
    0.65
     Lead
    0.65
    blers
    0.63
    wark
    0.62
    wright
    0.62
     rou
    0.62
     Mahjong
    0.61
     captcha
    0.61
    Act Density 0.159%

    No Known Activations