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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social and cultural critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Persistent
    -0.15
    edula
    -0.15
    Bubble
    -0.15
    kea
    -0.14
    ût
    -0.14
    ìĪ
    -0.14
     Yug
    -0.14
     cab
    -0.13
    ystal
    -0.13
    ÙĦÙī
    -0.13
    POSITIVE LOGITS
     Haven
    0.15
    adaÅŁ
    0.15
    enson
    0.14
    .Ordinal
    0.14
    achable
    0.14
    ÄĮesk
    0.14
    ks
    0.14
    à¥Įल
    0.14
    imos
    0.13
    venient
    0.13
    Act Density 0.048%

    No Known Activations