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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating relationships or causal connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ains
    -0.15
    .scalablytyped
    -0.14
     however
    -0.14
    _LP
    -0.14
     dissent
    -0.14
    uš
    -0.14
     tuy
    -0.13
     jedoch
    -0.13
    elda
    -0.13
    /power
    -0.13
    POSITIVE LOGITS
     nor
    0.30
    nor
    0.25
     Nor
    0.24
    Nor
    0.23
    ä¹Łä¸į
    0.18
    ä¸Ķ
    0.18
     neither
    0.17
     NOR
    0.17
    nder
    0.16
     geen
    0.16
    Act Density 0.189%

    No Known Activations