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

    Neuronpedia

    INDEX
    Explanations

    specific acronyms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the acronym "PU" and variations of it in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Heard
    -0.76
     Angels
    -0.75
     Esper
    -0.75
     Siren
    -0.71
    heimer
    -0.71
     Europeans
    -0.68
     Bermuda
    -0.67
     adm
    -0.66
    eworld
    -0.64
     Remain
    -0.64
    POSITIVE LOGITS
    BLIC
    1.71
    PDATE
    1.30
    PU
    1.20
    yip
    1.02
    ZZ
    0.98
    cci
    0.98
    cture
    0.96
    FFER
    0.94
    pload
    0.90
    resents
    0.90
    Act Density 0.010%

    No Known Activations