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

    Neuronpedia

    INDEX
    Explanations

    conjunctions, connecting words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukong
    -0.82
    ãĥ¤
    -0.76
    actory
    -0.71
    Nusra
    -0.71
    -------
    -0.70
    éŃĶ
    -0.68
     Loren
    -0.68
    lot
    -0.67
    blems
    -0.67
    Float
    -0.66
    POSITIVE LOGITS
     other
    0.90
     elsewhere
    0.76
     hence
    0.74
     otherwise
    0.74
     telecommunications
    0.73
    /
    0.72
     fitness
    0.72
     assorted
    0.71
     thereby
    0.70
     parenting
    0.69
    Act Density 0.331%

    No Known Activations