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

    Neuronpedia

    INDEX
    Explanations

    mentions of official statements or declarations made in press releases or emails

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in a" or "in an"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.74
     %%
    -0.67
     murderer
    -0.62
     needs
    -0.59
    icter
    -0.57
    )-
    -0.57
     unemploy
    -0.56
     needles
    -0.55
    haven
    -0.55
     istg
    -0.55
    POSITIVE LOGITS
     unison
    1.12
     response
    0.92
     lieu
    0.91
     regards
    0.86
     reply
    0.83
     conjunction
    0.81
     accordance
    0.79
    humane
    0.77
     remarks
    0.76
     advance
    0.75
    Act Density 0.067%

    No Known Activations