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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and words indicating relationships between ideas or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¹³
    -0.17
    бина
    -0.15
     ÐĵÑĢи
    -0.14
     singleton
    -0.14
     early
    -0.14
    orno
    -0.14
    icrous
    -0.13
    ุà¸ļ
    -0.13
    Unt
    -0.13
     UNUSED
    -0.13
    POSITIVE LOGITS
     indirect
    0.99
     indirectly
    0.78
     INDIRECT
    0.69
    irect
    0.40
    -direct
    0.34
     direct
    0.33
     Direct
    0.32
    direct
    0.31
    оÑģÑĢед
    0.30
    Direct
    0.30
    Act Density 0.010%

    No Known Activations