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

    Neuronpedia

    INDEX
    Explanations

    numbers and time-related terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to time, particularly durations and significant events in life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Highlights
    -0.57
     Lines
    -0.51
     encoding
    -0.51
     Structure
    -0.50
    yne
    -0.49
     Commentary
    -0.48
     Rack
    -0.47
    abad
    -0.47
    oria
    -0.47
     Listen
    -0.47
    POSITIVE LOGITS
    });
    0.70
    til
    0.65
    fo
    0.64
    etheless
    0.63
    aturday
    0.61
    aneously
    0.57
    })
    0.56
    heartedly
    0.56
    MpServer
    0.55
    ]);
    0.52
    Act Density 1.361%

    No Known Activations