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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing opinions and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     }}$}
    -0.67
    otry
    -0.62
    })*/
    -0.60
    LElement
    -0.59
     '\\;'
    -0.57
    Попис
    -0.57
     photolibrary
    -0.56
     Fg
    -0.55
    ipment
    -0.54
    ^(@)
    -0.54
    POSITIVE LOGITS
     Winaray
    0.64
     underrated
    0.55
    Cyfeiriadau
    0.52
    صیلات
    0.52
     oh
    0.51
    Omg
    0.51
     obsessed
    0.50
    دانشنامهٔ
    0.49
     omg
    0.49
    OMG
    0.49
    Act Density 0.125%

    No Known Activations