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

    Neuronpedia

    INDEX
    Explanations

    phrases related to blocking or obstruction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulfilled
    -0.16
    ves
    -0.15
    ming
    -0.15
    Äħż
    -0.15
    ä¸įåĪ°
    -0.14
    vem
    -0.14
    -0.14
    ÌĨ
    -0.14
    ux
    -0.14
    TY
    -0.13
    POSITIVE LOGITS
    busters
    0.19
    enheim
    0.17
    chains
    0.17
    quote
    0.17
    buster
    0.16
    pedia
    0.16
    stant
    0.16
     tuá»ķi
    0.16
    aded
    0.15
    pipes
    0.15
    Act Density 0.029%

    No Known Activations