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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of placing or positioning something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucci
    -0.72
    SB
    -0.71
    issance
    -0.69
    hess
    -0.64
    tub
    -0.61
    agher
    -0.60
    ery
    -0.59
    arb
    -0.59
    mpeg
    -0.58
    esome
    -0.58
    POSITIVE LOGITS
     bets
    1.14
     emphasis
    1.07
     blame
    1.01
    holders
    0.97
    holder
    0.92
     constraints
    0.79
     restrictions
    0.79
     undue
    0.78
     restraints
    0.78
     cursor
    0.78
    Act Density 0.057%

    No Known Activations