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

    Neuronpedia

    INDEX
    Explanations

    references to financial institutions like banks

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "bank."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Horton
    -0.75
    Rust
    -0.74
     Loving
    -0.72
    ————————————————
    -0.70
     Whedon
    -0.67
     Ake
    -0.67
    Else
    -0.66
     Hawth
    -0.65
    ————
    -0.64
    mite
    -0.63
    POSITIVE LOGITS
    rupt
    1.08
    notes
    1.06
    roll
    1.02
    rolled
    1.02
    note
    0.91
    sters
    0.89
     robber
    0.88
    rarily
    0.87
    redit
    0.82
    rolling
    0.82
    Act Density 0.020%

    No Known Activations