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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "refer" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hone
    -0.17
    é¾Ħ
    -0.17
     Wet
    -0.15
    .hwp
    -0.15
    FileVersion
    -0.15
     Crack
    -0.14
    èħ¹
    -0.14
    à¸łà¸²à¸ŀ
    -0.14
    æħİ
    -0.14
    ington
    -0.14
    POSITIVE LOGITS
    encias
    0.33
    encia
    0.28
    encies
    0.27
    enced
    0.25
    enties
    0.25
    encing
    0.25
    è
    0.25
    endum
    0.24
    enz
    0.22
    enci
    0.22
    Act Density 0.008%

    No Known Activations