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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and expressions of positivity related to collaboration or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    activex
    -0.17
    .kode
    -0.16
    tvrt
    -0.16
    .gridColumn
    -0.16
    ë¹Ļ
    -0.15
    аÑĢаÑĤ
    -0.15
    ÅĽcie
    -0.14
    .synthetic
    -0.14
    bourg
    -0.14
    riter
    -0.14
    POSITIVE LOGITS
     etc
    0.20
    /or
    0.19
    etc
    0.16
     overall
    0.15
     other
    0.15
     dig
    0.14
     otherwise
    0.14
    DoubleClick
    0.14
     Rus
    0.14
    beiter
    0.14
    Act Density 0.172%

    No Known Activations