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

    Neuronpedia

    INDEX
    Explanations

    structures and patterns in mathematical equations or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ')->
    -0.16
    >(()
    -0.15
     together
    -0.15
    chein
    -0.14
    ())->
    -0.14
    ottes
    -0.14
    abb
    -0.14
    648
    -0.14
     Tub
    -0.14
    ital
    -0.14
    POSITIVE LOGITS
    )+
    0.53
    ")+
    0.52
    ')+
    0.49
    ]+
    0.44
    )+(
    0.44
    ']+
    0.42
    )+↵
    0.41
    ]+\
    0.38
    ))+
    0.35
    )+"
    0.33
    Act Density 0.141%

    No Known Activations