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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and variable representations in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ^K
    -0.17
    ÃŃt
    -0.17
    ).*
    -0.17
     Escorts
    -0.15
     certain
    -0.15
     Herr
    -0.15
    anging
    -0.15
    è·¡
    -0.15
     Certain
    -0.14
     Shr
    -0.14
    POSITIVE LOGITS
    âĪ
    0.25
    _star
    0.24
    -star
    0.21
    istar
    0.20
     star
    0.20
     âĪ
    0.20
     starred
    0.20
    зв
    0.19
    ï¼Ĭ
    0.19
    _ast
    0.19
    Act Density 0.047%

    No Known Activations