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

    Neuronpedia

    INDEX
    Explanations

    phrases related to returning or resuming activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "back" indicating a return or復帰

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sudden
    -0.62
     background
    -0.61
     Sorceress
    -0.61
     pall
    -0.60
     inacc
    -0.59
     unintended
    -0.56
     regard
    -0.56
     Conrad
    -0.56
     chain
    -0.55
    uary
    -0.55
    POSITIVE LOGITS
    tracking
    1.26
    ped
    1.18
    stab
    1.13
    packing
    1.06
    packs
    1.03
    lit
    1.01
    dro
    1.00
    dated
    1.00
    track
    0.99
    dating
    0.97
    Act Density 0.044%

    No Known Activations