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

    Neuronpedia

    INDEX
    Explanations

    references to objects or entities within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĪ»
    -0.15
    znam
    -0.14
    asted
    -0.14
    agi
    -0.14
    @brief
    -0.14
    oley
    -0.14
    okus
    -0.14
    emen
    -0.13
    each
    -0.13
    uts
    -0.13
    POSITIVE LOGITS
     formats
    0.22
     stages
    0.21
     entirety
    0.20
     halves
    0.19
     install
    0.17
    ODULE
    0.16
     formato
    0.16
    Ú
    0.16
     format
    0.16
     batches
    0.15
    Act Density 0.199%

    No Known Activations