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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve stating or affirming conditions or realities

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

    Follows "that" and precedes "is"

    np_acts-logits-general · gemini-2.0-flash

    that is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.63
    TypedDataSet
    -0.59
    AlterField
    -0.58
    getExtras
    -0.58
     <=",
    -0.57
    +#+#
    -0.57
    hoga
    -0.53
     Numerade
    -0.53
    ArgumentParser
    -0.53
     kháng
    -0.53
    POSITIVE LOGITS
     decir
    0.94
     say
    0.78
    prnewswire
    0.77
     cioè
    0.75
     seja
    0.67
    ']));
    0.61
    say
    0.61
     znaczy
    0.61
    saying
    0.60
    ]));
    0.60
    Act Density 0.121%

    No Known Activations