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

    Neuronpedia

    INDEX
    Explanations

    comparisons involving value or worth in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ixel
    -0.15
    quate
    -0.15
    ?action
    -0.14
     {{{
    -0.14
     trigger
    -0.14
    anos
    -0.13
    uros
    -0.13
    ogl
    -0.13
    .Syntax
    -0.13
    _UID
    -0.13
    POSITIVE LOGITS
     thematic
    0.21
     queens
    0.20
     positional
    0.19
     Pills
    0.19
     Naj
    0.18
     fian
    0.18
     White
    0.17
     exchanges
    0.16
    counter
    0.16
     Minor
    0.16
    Act Density 0.003%

    No Known Activations