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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to individuals, particularly in the context of relationships or mental health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.67
     MotionEvent
    -0.59
    StoryboardSegue
    -0.58
    ValueStyle
    -0.57
     '{@
    -0.55
     Reli
    -0.51
    volley
    -0.51
    ]}"
    -0.50
     nakalista
    -0.50
    PRI
    -0.50
    POSITIVE LOGITS
    RegistryLite
    0.84
    قرير
    0.68
    horabuena
    0.67
    脚注の使い方
    0.66
    سجيل
    0.63
    -------------</
    0.62
    phosa
    0.60
     iParam
    0.60
    EndContext
    0.58
    joba
    0.56
    Act Density 0.066%

    No Known Activations