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

    Neuronpedia

    INDEX
    Explanations

    concepts related to flags and indicators of caution or warning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Weaver
    -0.15
    éĹ
    -0.15
    .XR
    -0.14
    ķĮ
    -0.14
    ardon
    -0.14
    555
    -0.14
    átek
    -0.14
    imdi
    -0.14
    etsk
    -0.14
    herits
    -0.14
    POSITIVE LOGITS
     A
    0.15
    ालà¤ķ
    0.15
     pl
    0.14
    ica
    0.14
    ad
    0.14
    ongs
    0.14
    fel
    0.13
    iving
    0.13
     An
    0.13
     camp
    0.13
    Act Density 0.303%

    No Known Activations