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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with a time expression followed by a verb in present continuous tense

    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
    enary
    -0.77
    orem
    -0.73
    uber
    -0.69
    onym
    -0.67
    ahu
    -0.66
    robe
    -0.65
    irc
    -0.65
    ocl
    -0.65
    irie
    -0.63
    ery
    -0.63
    POSITIVE LOGITS
     albeit
    1.29
     although
    1.25
     though
    1.18
     namely
    1.15
     however
    1.14
     especially
    1.10
     whereas
    1.01
     including
    1.01
     but
    1.00
     particularly
    0.94
    Act Density 0.568%

    No Known Activations