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

    Neuronpedia

    INDEX
    Explanations

    terms related to interests and expertise in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NewReader
    -0.64
     AssemblyCulture
    -0.63
     esternos
    -0.60
     createSprite
    -0.58
     honte
    -0.56
     LUMP
    -0.55
    ---+
    -0.53
    Чыганаклар
    -0.49
    AutoresizingMask
    -0.48
     ['./
    -0.48
    POSITIVE LOGITS
     interest
    3.69
    interest
    3.23
     Interest
    3.13
     INTEREST
    3.05
    Interest
    3.02
     interests
    2.88
    INTEREST
    2.77
     interested
    2.74
     interés
    2.49
     interes
    2.45
    Act Density 0.479%

    No Known Activations