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

    Neuronpedia

    INDEX
    Explanations

    phrases related to anticipation and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riteln
    -0.17
    odb
    -0.16
    enville
    -0.16
    ician
    -0.15
    ritel
    -0.15
    .UTC
    -0.15
    engo
    -0.15
    orne
    -0.15
    ermalink
    -0.15
    cko
    -0.14
    POSITIVE LOGITS
    ee
    0.15
    нина
    0.15
    VO
    0.14
    ops
    0.14
    eÄį
    0.14
     Nested
    0.14
    кÑĥлÑĮ
    0.14
     Rounded
    0.13
    à¹Ģหล
    0.13
    ми
    0.13
    Act Density 0.270%

    No Known Activations