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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases indicating relationships or discussions about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ummer
    -0.15
    OUNDS
    -0.14
    otre
    -0.14
    ez
    -0.13
     же
    -0.13
    iring
    -0.13
    ENO
    -0.13
    пон
    -0.13
    Ŀ¼
    -0.13
    ife
    -0.13
    POSITIVE LOGITS
     how
    0.24
    ureau
    0.19
     behalf
    0.17
     whether
    0.17
     cómo
    0.15
    atters
    0.15
    å¦Ĥä½ķ
    0.15
    FX
    0.15
     matters
    0.15
    how
    0.15
    Act Density 0.324%

    No Known Activations