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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions and expressions related to definitions and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hydrate
    -0.17
     flor
    -0.17
    otte
    -0.16
    ULT
    -0.15
     Jarvis
    -0.15
    AMIL
    -0.14
    rale
    -0.14
    205
    -0.14
    achte
    -0.14
    zee
    -0.14
    POSITIVE LOGITS
     defined
    0.35
    defined
    0.33
     Defined
    0.31
     definition
    0.31
     Definition
    0.27
    å®ļä¹ī
    0.26
    Defined
    0.25
     definitions
    0.25
    definition
    0.25
    Definition
    0.25
    Act Density 0.250%

    No Known Activations