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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time frames and ongoing processes

    oai_token-act-pair · gpt-3.5-turbo

    references to recovery or stages of recovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surpr
    -0.89
    SPONSORED
    -0.78
     furthermore
    -0.75
    else
    -0.75
    uci
    -0.70
     instead
    -0.70
     alone
    -0.70
     teasp
    -0.69
     secondly
    -0.69
     implicitly
    -0.69
    POSITIVE LOGITS
     rollout
    0.88
     backlog
    0.88
     approvals
    0.74
     horizon
    0.70
     pace
    0.70
     heels
    0.70
     ObamaCare
    0.68
     wildfires
    0.67
     embattled
    0.67
     aftermath
    0.67
    Act Density 0.696%

    No Known Activations