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

    Neuronpedia

    INDEX
    Explanations

    terms related to low-quality or undesirable items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ddf
    -0.16
    /animate
    -0.15
    tps
    -0.14
    ramid
    -0.14
    âm
    -0.14
    ocha
    -0.14
    vailability
    -0.13
    irim
    -0.13
     Lah
    -0.13
    ocate
    -0.13
    POSITIVE LOGITS
    ie
    1.02
    ies
    0.74
    IE
    0.73
     ie
    0.69
    -ie
    0.67
     IE
    0.63
    ief
    0.57
    iew
    0.56
    iez
    0.56
    _ie
    0.55
    Act Density 0.102%

    No Known Activations