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

    Neuronpedia

    INDEX
    Explanations

    negative conjunctions and their corresponding verbs in a context suggesting limitation or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tonsoft
    -0.59
     SAX
    -0.57
     чому
    -0.57
     Cæsar
    -0.55
    sief
    -0.55
    SAX
    -0.54
     quadr
    -0.53
     pleaf
    -0.53
    นวน
    -0.53
     estimat
    -0.52
    POSITIVE LOGITS
    neither
    1.81
     neither
    1.80
     Neither
    1.68
    Neither
    1.66
     nor
    1.63
    Nor
    1.43
     Nor
    1.42
    nor
    1.33
     NOR
    1.24
     tampoco
    1.21
    Act Density 0.096%

    No Known Activations