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

    Neuronpedia

    INDEX
    Explanations

    years or dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    locations and names of museums or theaters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omething
    -0.76
    ccording
    -0.72
    vernment
    -0.67
    staking
    -0.62
    ensibly
    -0.62
     reconc
    -0.59
     scram
    -0.59
     sort
    -0.58
     scrambling
    -0.58
     compromises
    -0.56
    POSITIVE LOGITS
     ********************************
    0.71
    <|endoftext|>
    0.71
    aceae
    0.67
    pmwiki
    0.66
     0004
    0.65
     UCHIJ
    0.65
     NX
    0.64
     Remix
    0.64
     4090
    0.64
     =====
    0.63
    Act Density 0.192%

    No Known Activations