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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or absence of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maj
    -0.16
    ARGET
    -0.15
    opo
    -0.15
    arrera
    -0.15
    à¹Īà¹Ģà¸Ľ
    -0.15
    ubar
    -0.14
    .Fields
    -0.14
    ingga
    -0.13
    WidgetItem
    -0.13
    bir
    -0.13
    POSITIVE LOGITS
     hidden
    0.26
     somewhere
    0.25
    hidden
    0.23
     elsewhere
    0.22
    Hidden
    0.22
     concealed
    0.20
    éļIJèĹı
    0.20
    _hidden
    0.20
     unknown
    0.19
    -hidden
    0.19
    Act Density 0.228%

    No Known Activations