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

    Neuronpedia

    INDEX
    Explanations

    instances of the concept of explanation and clarity in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    خاÙĨÙĩ
    -0.16
    presso
    -0.15
    ilver
    -0.14
    rey
    -0.14
    ikal
    -0.14
    /from
    -0.14
    chet
    -0.14
    readcr
    -0.14
    ffective
    -0.13
    å®ħ
    -0.13
    POSITIVE LOGITS
     why
    0.28
     away
    0.28
     Away
    0.27
    -away
    0.24
    away
    0.24
    Away
    0.23
    为ä»Ģä¹Ī
    0.23
    why
    0.20
     briefly
    0.17
    Fully
    0.17
    Act Density 0.025%

    No Known Activations