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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical symbols and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     than
    -0.16
    bach
    -0.15
     lug
    -0.15
    ins
    -0.14
    aj
    -0.14
     Guardian
    -0.14
     str
    -0.14
    Count
    -0.14
    VP
    -0.14
    anch
    -0.14
    POSITIVE LOGITS
    ozem
    0.20
    ushi
    0.16
    dete
    0.15
    wald
    0.15
    erin
    0.15
    inden
    0.15
    /Instruction
    0.15
    åģ¥
    0.14
    -Methods
    0.14
    wi
    0.14
    Act Density 0.022%

    No Known Activations