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

    Neuronpedia

    INDEX
    Explanations

    phrases related to entering agreements, partnerships, or competitions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    attribute
    -0.65
    obe
    -0.64
    cks
    -0.64
    killer
    -0.63
    killers
    -0.62
    roller
    -0.62
    bara
    -0.61
    die
    -0.58
    iggs
    -0.58
    alm
    -0.58
    POSITIVE LOGITS
    prising
    1.42
     into
    1.19
    tain
    1.08
    prises
    1.03
    prise
    1.01
     INTO
    1.01
    TAIN
    0.96
    tained
    0.94
    into
    0.91
    taining
    0.90
    Act Density 0.038%

    No Known Activations