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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases such as durations or time periods

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to the duration of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUn
    -0.97
    obin
    -0.73
    agate
    -0.69
    egu
    -0.66
    umbn
    -0.66
    ragon
    -0.63
    ãĤ´ãĥ³
    -0.62
    gger
    -0.61
    acus
    -0.61
    ãĤ¨ãĥ«
    -0.61
    POSITIVE LOGITS
     sake
    0.82
    pires
    0.64
    IENCE
    0.63
    nar
    0.62
    ruary
    0.60
     silence
    0.60
    !--
    0.59
     Hung
    0.58
     Indones
    0.57
    EAR
    0.57
    Act Density 0.080%

    No Known Activations