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

    Neuronpedia

    INDEX
    Explanations

    actions related to taking, giving, or cutting ties and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     formerly
    -0.43
    CodeAttribute
    -0.39
     also
    -0.38
    formerly
    -0.37
    Описание
    -0.37
     recently
    -0.36
     especially
    -0.36
     appunto
    -0.35
     finally
    -0.35
     previously
    -0.34
    POSITIVE LOGITS
     themſelves
    0.75
     auroit
    0.74
     daisies
    0.74
     breadcrumbs
    0.71
     themselves
    0.70
     EVERYTHING
    0.70
     jokes
    0.69
     feroit
    0.69
     verſch
    0.68
    majánló
    0.68
    Act Density 0.847%

    No Known Activations