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

    Neuronpedia

    INDEX
    Explanations

    terms related to categorization and classification within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abstrait
    -0.71
    setAccessible
    -0.71
    styleType
    -0.71
     vettor
    -0.69
    Xna
    -0.69
     EnglishChoose
    -0.68
     movimenti
    -0.66
     avoient
    -0.66
    InstanceState
    -0.66
    IsContent
    -0.65
    POSITIVE LOGITS
    脚注の使い方
    0.77
     diligen
    0.61
     constat
    0.55
    Dichloroethene
    0.54
    WRITER
    0.54
    avadoc
    0.54
    adox
    0.53
    :]:
    0.52
     vesti
    0.51
     imageNamed
    0.51
    Act Density 0.948%

    No Known Activations