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

    Neuronpedia

    INDEX
    Explanations

    terms related to "interests" and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prefixer
    -0.63
    +#+#
    -0.62
     >=",
    -0.61
    AddTagHelper
    -0.56
    rungsseite
    -0.56
    expandindo
    -0.54
    Jeografia
    -0.54
    ValueStyle
    -0.53
    Aholisi
    -0.53
    Хьажоргаш
    -0.52
    POSITIVE LOGITS
     interested
    0.71
     Interested
    0.62
     interes
    0.62
     interess
    0.60
     interests
    0.60
     intéress
    0.60
     INTEREST
    0.58
    Interested
    0.56
     wing
    0.56
     заинтере
    0.55
    Act Density 0.172%

    No Known Activations