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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols that indicate important or unique elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctype
    -0.15
     Floor
    -0.15
    âĻª
    -0.14
    询
    -0.14
    etta
    -0.14
    ambre
    -0.14
    Beam
    -0.13
    brands
    -0.13
    aravel
    -0.13
     type
    -0.13
    POSITIVE LOGITS
     Ca
    0.17
    -corner
    0.15
     Segment
    0.15
     Dogs
    0.15
    Segment
    0.14
     Caul
    0.14
    Ca
    0.14
     CA
    0.14
    ziej
    0.14
     sector
    0.14
    Act Density 0.006%

    No Known Activations