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

    Neuronpedia

    INDEX
    Explanations

    adverbs and their variations indicating manner or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.19
    TriState
    -0.16
    //{{
    -0.15
    ÏĮμε
    -0.15
    ternet
    -0.15
    ControlItem
    -0.14
    pmat
    -0.14
    :normal
    -0.14
    phan
    -0.14
    inha
    -0.14
    POSITIVE LOGITS
    ly
    0.22
    ness
    0.18
    NESS
    0.18
     yet
    0.17
    elly
    0.17
    LY
    0.16
     await
    0.16
     Pul
    0.15
    ely
    0.15
     cons
    0.15
    Act Density 0.087%

    No Known Activations