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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of returning

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with returns and the act of coming back

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uren
    -0.68
    inas
    -0.66
    nel
    -0.61
     INCLUD
    -0.61
    heid
    -0.60
    stood
    -0.60
    arios
    -0.59
    okane
    -0.59
    rican
    -0.58
    rouse
    -0.58
    POSITIVE LOGITS
     reinforcements
    0.92
     refreshed
    0.85
     vengeance
    0.77
     whence
    0.76
    rocal
    0.71
     rejuven
    0.71
     blessings
    0.70
     rightful
    0.66
     haunt
    0.66
    alkyrie
    0.66
    Act Density 0.169%

    No Known Activations