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

    Neuronpedia

    INDEX
    Explanations

    key transitional or relational phrases that connect ideas or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iring
    -0.15
    èĬĤ
    -0.15
    immel
    -0.14
    iry
    -0.14
    akedown
    -0.14
    одаÑĢ
    -0.14
    Wer
    -0.14
    ocy
    -0.14
     Wer
    -0.14
    asar
    -0.14
    POSITIVE LOGITS
    .OP
    0.14
    uilder
    0.14
    ظاÙħ
    0.14
    culate
    0.14
     Dere
    0.14
    .exam
    0.13
    _COMPILE
    0.13
    /Gate
    0.13
    OX
    0.13
    ãģĿ
    0.13
    Act Density 0.001%

    No Known Activations