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

    Neuronpedia

    INDEX
    Explanations

    concepts related to decision-making and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aille
    -0.19
    ãĥ¬ãĥĥãĥĪ
    -0.18
    .scalablytyped
    -0.17
    imedia
    -0.17
    loub
    -0.15
    uster
    -0.15
    ÙĪبة
    -0.15
    iper
    -0.14
    lasses
    -0.14
    ủng
    -0.14
    POSITIVE LOGITS
     Shall
    0.17
    ucky
    0.17
    /how
    0.16
    JJ
    0.15
     shall
    0.15
    tron
    0.15
    enti
    0.15
     destiny
    0.15
     fate
    0.14
     Conrad
    0.14
    Act Density 0.182%

    No Known Activations