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

    Neuronpedia

    INDEX
    Explanations

    comparisons between pros and cons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edReader
    -0.21
    hip
    -0.19
    hood
    -0.19
    -vous
    -0.18
    hips
    -0.18
    ously
    -0.17
    stown
    -0.16
    rophe
    -0.16
    edback
    -0.16
    uality
    -0.16
    POSITIVE LOGITS
    Ùij
    0.18
     à¹Ĩ
    0.16
    ri
    0.16
    à¹Ĩ
    0.15
    ãĢħ
    0.14
    uti
    0.14
    ded
    0.14
    acer
    0.14
    sut
    0.14
    dest
    0.14
    Act Density 0.479%

    No Known Activations