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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical locations or settings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "back" and associated concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pitt
    -0.88
    inas
    -0.72
    ãģ®éŃĶ
    -0.70
    rano
    -0.68
    PF
    -0.67
    ioxide
    -0.67
    CLE
    -0.66
    VOL
    -0.65
    76561
    -0.65
    IUM
    -0.64
    POSITIVE LOGITS
     hive
    0.69
    puff
    0.67
     carpet
    0.64
    xual
    0.63
    backer
    0.63
    runs
    0.63
     trail
    0.62
     Scully
    0.61
     shuffle
    0.61
    edly
    0.60
    Act Density 0.059%

    No Known Activations