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

    Neuronpedia

    INDEX
    Explanations

    compound or complex conjunctions and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.67
     culminating
    -0.60
     sighing
    -0.59
     costing
    -0.57
     blooming
    -0.57
    contentLoaded
    -0.56
    Sucesor
    -0.56
     affecting
    -0.55
     initComponents
    -0.54
     serem
    -0.54
    POSITIVE LOGITS
     has
    1.28
     had
    1.12
     have
    1.06
     took
    1.03
     is
    0.99
     enjoys
    0.97
     got
    0.94
     can
    0.93
     knew
    0.91
     will
    0.91
    Act Density 0.702%

    No Known Activations