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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and accompanying phrases that connect ideas or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    寧
    -0.14
     Sle
    -0.14
    sat
    -0.13
    ECTOR
    -0.13
    anel
    -0.13
    ANEL
    -0.13
    á»įt
    -0.13
    ubb
    -0.12
    culate
    -0.12
    nero
    -0.12
    POSITIVE LOGITS
     although
    0.24
    although
    0.21
     nowhere
    0.18
    this
    0.18
    Although
    0.17
     whereas
    0.17
     though
    0.17
    it
    0.16
     Although
    0.16
     it
    0.16
    Act Density 0.341%

    No Known Activations