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

    Neuronpedia

    INDEX
    Explanations

    references to comparisons and relationships among different groups or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.51
    snapshot
    -0.49
     #%
    -0.48
     I
    -0.48
     D
    -0.47
    Koala
    -0.45
     Prow
    -0.45
    ValueStyle
    -0.45
     regia
    -0.45
    шру
    -0.44
    POSITIVE LOGITS
     colleagues
    1.05
     colleague
    1.03
     colega
    0.90
     colegas
    0.90
     counterparts
    0.90
     rekan
    0.88
     fellow
    0.88
     Colleagues
    0.86
     collègues
    0.84
     predecessors
    0.84
    Act Density 0.187%

    No Known Activations