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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "any" followed by a positive adjective

    oai_token-act-pair · gpt-3.5-turbo

    the term "any" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aver
    -0.75
     coupled
    -0.68
     rise
    -0.57
     evolved
    -0.57
     grind
    -0.55
     prey
    -0.55
     better
    -0.55
     Demons
    -0.55
     constrained
    -0.54
     lubric
    -0.54
    POSITIVE LOGITS
    any
    4.43
    ANY
    2.65
    anyl
    1.58
    anything
    1.54
    Any
    1.47
    ani
    1.42
    ony
    1.37
    ania
    1.37
    anya
    1.34
     Any
    1.29
    Act Density 0.015%

    No Known Activations