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

    Neuronpedia

    INDEX
    Explanations

    references to characters or entities in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leÅŁ
    -0.14
    awl
    -0.13
     kas
    -0.13
    Å¡li
    -0.13
    agn
    -0.13
    oins
    -0.13
     Sap
    -0.13
    rana
    -0.13
    arna
    -0.13
    placeholders
    -0.13
    POSITIVE LOGITS
     aforementioned
    0.26
    åĪļæīį
    0.20
     вÑĭÑĪе
    0.19
     afore
    0.17
    ulty
    0.15
     mentioned
    0.15
    IMIT
    0.15
     above
    0.15
    IVEN
    0.15
    .yy
    0.15
    Act Density 0.111%

    No Known Activations