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

    Neuronpedia

    INDEX
    Explanations

    concepts related to budgeting and financial decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rint
    -0.14
    ãĥ³ãĥĩ
    -0.13
    /*č↵
    -0.13
    AffineTransform
    -0.13
    inia
    -0.12
    ä¸Ķ
    -0.12
     prostÅĻednictvÃŃm
    -0.12
    ìĥģìĿĺ
    -0.12
    /compiler
    -0.12
    DITION
    -0.12
    POSITIVE LOGITS
     refers
    0.48
     refer
    0.41
     referring
    0.38
    ãģ¨ãģ¯
    0.35
    refer
    0.31
    ëŀĢ
    0.30
     means
    0.30
     meaning
    0.30
     describes
    0.28
     Meaning
    0.28
    Act Density 0.565%

    No Known Activations