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

    Neuronpedia

    INDEX
    Explanations

    terms related to machine learning modeling and structural analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quæ
    -0.95
     feroit
    -0.95
     ejus
    -0.93
     auroit
    -0.91
     ainfi
    -0.88
     quelcon
    -0.87
     avoient
    -0.86
     malheure
    -0.81
    __':
    -0.81
     malheureux
    -0.81
    POSITIVE LOGITS
     test
    0.65
     string
    0.54
    ',...
    0.53
     model
    0.53
     }^{*}$
    0.51
     qu
    0.50
     train
    0.50
     oro
    0.50
     des
    0.49
    ...</
    0.49
    Act Density 0.996%

    No Known Activations