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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "all"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating groupings or collections of people or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHIP
    -0.67
    yip
    -0.67
    aminer
    -0.66
    IDS
    -0.63
    bal
    -0.62
    hift
    -0.61
    FH
    -0.61
    utsche
    -0.59
    grad
    -0.58
    abwe
    -0.58
    POSITIVE LOGITS
    ocating
    1.32
    ocated
    1.09
    igators
    1.03
    igator
    1.03
    usions
    1.01
    owing
    1.01
    uding
    1.00
    iances
    0.99
    usion
    0.93
    ocation
    0.92
    Act Density 0.113%

    No Known Activations