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

    Neuronpedia

    INDEX
    Explanations

    clusters of textual patterns and sequences that suggest verbosity or complexity in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assen
    -0.16
    blr
    -0.15
    obi
    -0.15
    DCF
    -0.15
    icode
    -0.14
     ogs
    -0.14
    essional
    -0.14
    สะ
    -0.14
    .gb
    -0.13
    eneral
    -0.13
    POSITIVE LOGITS
     sav
    0.18
    unter
    0.16
    adi
    0.16
    ured
    0.15
     cons
    0.15
     subsystem
    0.15
     Hunter
    0.14
    enk
    0.14
    rijk
    0.14
    AR
    0.13
    Act Density 0.000%

    No Known Activations