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

    Neuronpedia

    INDEX
    Explanations

    terms related to blocking or obstructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulfilled
    -0.18
    nder
    -0.17
    ux
    -0.16
    ussy
    -0.16
    ming
    -0.15
    istic
    -0.15
     Kitt
    -0.15
    ves
    -0.15
    onde
    -0.15
    ndern
    -0.14
    POSITIVE LOGITS
    busters
    0.26
    buster
    0.23
    aded
    0.20
    íĦ
    0.19
    ADED
    0.18
    enheim
    0.17
    edImage
    0.17
     tuá»ķi
    0.17
    quote
    0.17
    pipes
    0.16
    Act Density 0.043%

    No Known Activations