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

    Neuronpedia

    INDEX
    Explanations

    references to evidence and citations used in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scratch
    -0.16
    оже
    -0.15
    880
    -0.15
    rana
    -0.15
     scratches
    -0.14
    iram
    -0.14
    åĿ¦
    -0.14
    enable
    -0.14
     spl
    -0.13
     racing
    -0.13
    POSITIVE LOGITS
    à¹ģหล
    0.17
     MethodInfo
    0.16
     cita
    0.15
    edList
    0.15
    /sources
    0.15
    /source
    0.14
    scp
    0.14
    _FALL
    0.14
    ÐIJÑĢÑħÑĸв
    0.14
    heels
    0.14
    Act Density 0.213%

    No Known Activations