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

    Neuronpedia

    INDEX
    Explanations

    mentions of bounties or bounty hunters

    oai_token-act-pair · gpt-3.5-turbo

    references to bounties and bounty hunters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppard
    -0.86
    icken
    -0.76
     Reaction
    -0.72
    VW
    -0.70
    mus
    -0.69
    INK
    -0.68
     Ange
    -0.67
    ople
    -0.67
    inking
    -0.66
    case
    -0.66
    POSITIVE LOGITS
     bounty
    1.45
     bount
    1.29
     hunter
    1.26
     hunters
    1.08
     Bounty
    0.95
    iless
    0.88
     hunting
    0.84
    halla
    0.81
    iful
    0.81
     reward
    0.79
    Act Density 0.005%

    No Known Activations