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

    Neuronpedia

    INDEX
    Explanations

    terms related to strategies and interventions for various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    numerusform
    -0.63
     odkazy
    -0.60
     disambiguazione
    -0.58
    ContentLoaded
    -0.54
     houſe
    -0.53
    bited
    -0.52
     pleaſure
    -0.52
    XmlAccessorType
    -0.51
    hoeddwyd
    -0.51
     Happens
    -0.51
    POSITIVE LOGITS
     employed
    1.18
     adopted
    1.12
     devised
    1.06
    adopted
    0.98
    employed
    0.90
     Employed
    0.89
     developed
    0.88
     Adopted
    0.87
     methods
    0.81
     used
    0.81
    Act Density 0.621%

    No Known Activations