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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "so" indicating a cause-effect relationship or explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĥÑģÑĤа
    -0.15
    acher
    -0.15
    yme
    -0.15
    kke
    -0.14
    ceae
    -0.14
    ediator
    -0.14
    ä¸ĸ
    -0.14
    umba
    -0.14
    ullo
    -0.14
    ertino
    -0.14
    POSITIVE LOGITS
    ÅĻev
    0.16
    table
    0.15
    gle
    0.15
    iesen
    0.15
    िब
    0.14
    ALES
    0.14
    vention
    0.14
    ÏģιÏĥ
    0.14
    εβ
    0.14
     diss
    0.14
    Act Density 0.073%

    No Known Activations