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

    Neuronpedia

    INDEX
    Explanations

    words related to academic research studies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of studies or research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     volatile
    -0.63
     resonance
    -0.61
    rontal
    -0.61
    interstitial
    -0.60
    udeau
    -0.60
     deprecated
    -0.60
     blurred
    -0.60
     ILCS
    -0.60
    cream
    -0.59
     overloaded
    -0.58
    POSITIVE LOGITS
    study
    0.88
    udo
    0.81
    Study
    0.80
     statistic
    0.78
    iveness
    0.76
     methodology
    0.75
     study
    0.75
    ador
    0.72
     findings
    0.69
    ors
    0.69
    Act Density 0.028%

    No Known Activations