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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Any"

    oai_token-act-pair · gpt-3.5-turbo

    generic references to policies or statements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cru
    -0.79
    pez
    -0.63
     lives
    -0.62
     lament
    -0.60
     reapp
    -0.58
    FontSize
    -0.57
     figure
    -0.57
     figures
    -0.56
     coinc
    -0.56
     reign
    -0.55
    POSITIVE LOGITS
     Any
    3.24
    Any
    2.62
     Anything
    2.11
     Anyone
    1.92
    any
    1.87
     ANY
    1.81
    Anything
    1.79
     Whenever
    1.51
     Either
    1.49
    anything
    1.47
    Act Density 0.015%

    No Known Activations