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

    Neuronpedia

    INDEX
    Explanations

    phrases related to repeated occurrences or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating repeated processes or actions over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.84
    quart
    -0.69
    Surv
    -0.68
     CLIENT
    -0.65
    igers
    -0.64
     Receiver
    -0.63
     Supports
    -0.63
    \\\\\\\\\\\\\\\\
    -0.63
     Prot
    -0.62
    Prot
    -0.60
    POSITIVE LOGITS
     space
    0.96
     resources
    0.93
     effort
    0.89
     patience
    0.79
     place
    0.79
     money
    0.76
    space
    0.76
     locality
    0.76
     inclination
    0.76
     energy
    0.75
    Act Density 0.125%

    No Known Activations