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

    Neuronpedia

    INDEX
    Explanations

    words related to critique or negative assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernet
    -0.16
    sj
    -0.15
    ë§ĪíĬ¸
    -0.15
    ubl
    -0.15
    roker
    -0.14
    cq
    -0.14
    /stdc
    -0.14
    egas
    -0.14
    elib
    -0.14
    dens
    -0.13
    POSITIVE LOGITS
    present
    0.34
    search
    0.33
    volution
    0.32
    presentation
    0.30
    fer
    0.30
    stricted
    0.28
    lation
    0.28
    levant
    0.28
    commended
    0.27
    v
    0.27
    Act Density 0.012%

    No Known Activations