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

    Neuronpedia

    INDEX
    Explanations

    terms related to product sales and warranties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignal
    -0.17
    ëĭ¤ê°Ģ
    -0.16
    iences
    -0.15
    vil
    -0.14
     Stokes
    -0.14
    ÄĽr
    -0.14
    eggies
    -0.14
     Lesser
    -0.14
    atomy
    -0.13
    ocket
    -0.13
    POSITIVE LOGITS
    ss
    0.58
    sg
    0.52
    sm
    0.49
    sw
    0.47
    stype
    0.46
    ssp
    0.44
    sf
    0.44
    sv
    0.44
    sb
    0.42
    stime
    0.42
    Act Density 0.123%

    No Known Activations