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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Auf" and its variants, indicating a focus on phrases related to actions or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ched
    -0.18
    uv
    -0.16
    len
    -0.16
    l
    -0.15
    à¹ģà¸ģ
    -0.15
    xing
    -0.14
    æĻ¯
    -0.14
    elle
    -0.14
    iy
    -0.14
    unch
    -0.13
    POSITIVE LOGITS
     basis
    0.19
     Basis
    0.18
    relude
    0.17
    ritch
    0.16
    bau
    0.15
    enberg
    0.15
    division
    0.15
    holm
    0.15
     behalf
    0.15
    EFR
    0.15
    Act Density 0.010%

    No Known Activations