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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "time" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to recurring events or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exclusive
    -0.73
    agar
    -0.73
    eaturing
    -0.71
    agra
    -0.69
    yt
    -0.68
    querque
    -0.67
    ãĥĥãĥĪ
    -0.66
    orig
    -0.66
    arling
    -0.65
    inth
    -0.65
    POSITIVE LOGITS
     someone
    1.23
     somebody
    1.19
    soever
    1.01
     you
    0.96
     something
    0.95
     anyone
    0.93
     anybody
    0.92
    someone
    0.92
     imaginable
    0.87
     we
    0.87
    Act Density 0.077%

    No Known Activations