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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    иÑĤив
    -0.17
     Zag
    -0.15
    à¤Ĺर
    -0.15
    ith
    -0.15
    odes
    -0.15
    wan
    -0.15
    any
    -0.15
    ult
    -0.14
    byname
    -0.14
    _lite
    -0.14
    POSITIVE LOGITS
    amble
    0.16
    attice
    0.16
    OLON
    0.15
     Cain
    0.14
    rypt
    0.14
    สะ
    0.14
    ptune
    0.14
    dle
    0.14
     tiêu
    0.13
    obia
    0.13
    Act Density 0.057%

    No Known Activations