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

    Neuronpedia

    INDEX
    Explanations

    contextually significant words and phrases that highlight conditional or critical aspects of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucha
    -0.16
    .tap
    -0.15
    ष
    -0.15
    ש
    -0.15
    elter
    -0.14
    ruh
    -0.14
    qml
    -0.14
    studio
    -0.13
     Innoc
    -0.13
     Vog
    -0.13
    POSITIVE LOGITS
     mnemonic
    0.16
    erno
    0.15
     âĨij
    0.15
    ignum
    0.14
    utz
    0.14
     âĨĵ
    0.14
     neglect
    0.13
    endon
    0.13
    .dataTables
    0.13
    clusive
    0.13
    Act Density 0.001%

    No Known Activations