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

    Neuronpedia

    INDEX
    Explanations

    patterns indicating the presence of configuration or status codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.92
     propOrder
    -0.91
    InjectAttribute
    -0.85
    fjspx
    -0.83
     <",
    -0.81
     Spisak
    -0.79
    AsUp
    -0.78
    setVerticalGroup
    -0.78
    mergeFrom
    -0.77
     Himo
    -0.76
    POSITIVE LOGITS
    éndole
    0.73
    iVar
    0.61
    enumi
    0.55
     P
    0.53
     $
    0.51
     
    0.51
    _{
    0.50
     G
    0.50
    TimeoutException
    0.50
    extension
    0.49
    Act Density 0.040%

    No Known Activations