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

    Neuronpedia

    INDEX
    Explanations

    instances of the words "highest" and "lowest" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    r
    -0.83
    s
    -0.72
    u
    -0.70
    er
    -0.68
    l
    -0.66
    t
    -0.63
    sk
    -0.63
    en
    -0.60
    p
    -0.60
    н
    -0.60
    POSITIVE LOGITS
    aderie
    1.09
     виправивши
    1.06
    ]")]
    1.05
    FieldBuilder
    1.05
    QMetaType
    1.03
     nahilalakip
    1.00
     propOrder
    1.00
    elemField
    0.99
    annica
    0.98
    Hozzáférés
    0.98
    Act Density 0.014%

    No Known Activations