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

    Neuronpedia

    INDEX
    Explanations

    terms related to applications or uses of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IELD
    -0.71
     Bever
    -0.66
     Madness
    -0.66
    beard
    -0.66
     Ended
    -0.63
     SHARES
    -0.63
     Belt
    -0.62
     Reincarn
    -0.62
     Penet
    -0.61
    Fax
    -0.61
    POSITIVE LOGITS
    ators
    1.85
    ator
    1.70
    atory
    1.55
    ative
    1.51
    atorial
    1.42
    ational
    1.40
    atable
    1.30
    atives
    1.27
    atories
    1.23
    aton
    1.21
    Act Density 0.024%

    No Known Activations