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

    Neuronpedia

    INDEX
    Explanations

    recurrent phrases and expressions indicating preference or recommendation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufe
    -0.14
     gly
    -0.14
    izo
    -0.14
    atoria
    -0.13
     vin
    -0.13
    kel
    -0.13
    minent
    -0.13
    .Library
    -0.13
    quette
    -0.13
    orrent
    -0.13
    POSITIVE LOGITS
    idata
    0.17
    .AutoSizeMode
    0.15
    879
    0.15
    theless
    0.15
    olics
    0.14
    _cpus
    0.14
    داد
    0.14
    OSP
    0.14
    ossa
    0.14
    CONS
    0.14
    Act Density 0.168%

    No Known Activations