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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases referring to the end of a specified period

    oai_token-act-pair · gpt-3.5-turbo

    references to deadlines or endpoints of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.70
    htaking
    -0.70
    ufact
    -0.66
    avorite
    -0.65
    uni
    -0.65
    pload
    -0.64
    æ©Ł
    -0.63
    kaya
    -0.62
    anship
    -0.61
     Fired
    -0.61
    POSITIVE LOGITS
    owment
    1.35
    angering
    1.04
    ocrine
    0.98
    ocrin
    0.87
    orses
    0.83
    game
    0.80
    door
    0.79
    angered
    0.78
     thereof
    0.77
    orph
    0.76
    Act Density 0.031%

    No Known Activations