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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    plural nouns or noun phrases that are the subject of a sentence.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     itself
    -0.59
    itself
    -0.52
     Itself
    -0.46
    ness
    -0.41
    config
    -0.41
     has
    -0.41
    stuff
    -0.39
    9
    -0.39
     information
    -0.37
     Ed
    -0.36
    POSITIVE LOGITS
     berdua
    0.83
     neler
    0.82
     allemaal
    0.82
     wszyscy
    0.77
     kaikki
    0.76
     były
    0.75
     zijne
    0.75
    wolves
    0.74
     voltak
    0.74
     všetky
    0.73
    Act Density 0.537%

    No Known Activations