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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official statements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    the word "in" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.85
     %%
    -0.68
    estine
    -0.62
     unemploy
    -0.62
    76561
    -0.62
     experimented
    -0.60
    few
    -0.60
     artif
    -0.58
     penet
    -0.58
    /(
    -0.58
    POSITIVE LOGITS
     response
    1.04
     remarks
    0.99
     announcing
    0.95
     unison
    0.95
     conjunction
    0.87
    aug
    0.87
     explaining
    0.86
     reply
    0.85
     emailed
    0.83
     lieu
    0.83
    Act Density 0.072%

    No Known Activations