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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating social dynamics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avir
    -0.14
    ãĥ¼ãĥŃ
    -0.13
    оÑĢож
    -0.13
    ÙħاÙħ
    -0.13
    cil
    -0.12
    çķª
    -0.12
    pto
    -0.12
     nok
    -0.12
    ÅĤaw
    -0.12
    istani
    -0.12
    POSITIVE LOGITS
    .fm
    0.17
    iedo
    0.15
    .ibatis
    0.15
    à¸Ļà¸Ń
    0.15
    bane
    0.15
     ÑĥÑģÑĤ
    0.15
    ehr
    0.15
     Hass
    0.15
    etty
    0.14
     Infragistics
    0.14
    Act Density 0.199%

    No Known Activations