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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jaan
    -0.48
    .
    -0.42
     поводу
    -0.37
    Distances
    -0.37
    after
    -0.36
     ग्राहक
    -0.35
    INTA
    -0.34
    ;
    -0.34
    λευτα
    -0.34
     after
    -0.34
    POSITIVE LOGITS
     Theſe
    0.91
    Хьажоргаш
    0.84
    verwijspagina
    0.83
    #+#
    0.81
    ✨:
    0.76
    didSet
    0.76
     ſtate
    0.75
     Reſ
    0.75
     tartalomajánló
    0.74
     للاسماء
    0.70
    Act Density 0.810%

    No Known Activations