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

    Neuronpedia

    INDEX
    Explanations

    phrases related to research studies and publications

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nih
    -0.76
    tsy
    -0.67
    laughter
    -0.66
    angu
    -0.65
    ole
    -0.65
    grain
    -0.65
    sburg
    -0.65
    idi
    -0.64
    ikawa
    -0.64
    igmatic
    -0.63
    POSITIVE LOGITS
     however
    1.22
     meanwhile
    1.07
     moreover
    0.95
     comprising
    0.92
     along
    0.87
     consisting
    0.87
     dubbed
    0.87
     albeit
    0.86
     which
    0.85
     coupled
    0.85
    Act Density 0.135%

    No Known Activations