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

    Neuronpedia

    INDEX
    Explanations

    references to awards and recognitions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IGN
    -0.14
    irs
    -0.14
    -control
    -0.14
    ål
    -0.14
    avers
    -0.14
    chn
    -0.14
     Morrison
    -0.14
    aves
    -0.14
    agan
    -0.14
    blocks
    -0.13
    POSITIVE LOGITS
     awards
    0.24
     Awards
    0.22
     trao
    0.16
     rewards
    0.15
    gnore
    0.15
    Colors
    0.15
     Award
    0.15
     award
    0.14
    ategories
    0.14
    _simps
    0.14
    Act Density 0.058%

    No Known Activations