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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     strains
    -0.41
     provocation
    -0.38
     spas
    -0.38
     realistic
    -0.37
     realism
    -0.37
     visualization
    -0.37
     asemenea
    -0.37
     Bam
    -0.36
     manifestation
    -0.36
     specificity
    -0.36
    POSITIVE LOGITS
     للمعارف
    0.67
     GenerationType
    0.57
     noDo
    0.55
    KommentareTeilen
    0.54
    RepeatedField
    0.51
    Autoritní
    0.50
     صوتيه
    0.49
     Paglinawan
    0.47
    RegressionTest
    0.47
    tagHelperRunner
    0.47
    Act Density 0.001%

    No Known Activations