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

    Neuronpedia

    INDEX
    Explanations

    timestamps in a specific format (hours and minutes) in a series of texts

    oai_token-act-pair · gpt-3.5-turbo

    specific timestamps or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozo
    -0.83
     skelet
    -0.72
    operated
    -0.72
    abwe
    -0.72
    eele
    -0.71
    agos
    -0.66
    ubby
    -0.66
    hell
    -0.65
    oppable
    -0.64
    orc
    -0.64
    POSITIVE LOGITS
     03
    1.01
     02
    1.01
     05
    0.99
     06
    0.99
     04
    0.98
     07
    0.97
     09
    0.91
     08
    0.89
     01
    0.89
     00
    0.82
    Act Density 0.009%

    No Known Activations