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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional statements or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¾ãģł
    -0.17
    ä¸Ī
    -0.15
    arms
    -0.15
     chÆ°a
    -0.15
     zwar
    -0.14
    ringe
    -0.14
    ãģłãģ£ãģ¦
    -0.14
     à¤ħà¤Ń
    -0.14
    afa
    -0.14
     ÙĨدارد
    -0.14
    POSITIVE LOGITS
     Suff
    0.19
     generally
    0.16
    uela
    0.15
    å·®
    0.15
     suffice
    0.14
    oron
    0.14
    cka
    0.14
    hint
    0.14
    ekl
    0.14
     nick
    0.14
    Act Density 0.068%

    No Known Activations