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

    Neuronpedia

    INDEX
    Explanations

    mentions of conflicts of interest

    oai_token-act-pair · gpt-3.5-turbo

    references to conflicts of interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jelly
    -0.69
    LESS
    -0.65
    nz
    -0.64
     tv
    -0.62
     Dodge
    -0.62
     nas
    -0.62
     whence
    -0.61
    RAY
    -0.60
     perish
    -0.59
     starve
    -0.59
    POSITIVE LOGITS
    interest
    0.79
     Interest
    0.71
    Interest
    0.71
     interest
    0.68
    rontal
    0.67
     interests
    0.67
    contract
    0.66
    eties
    0.65
     conscience
    0.61
    ortunately
    0.61
    Act Density 0.093%

    No Known Activations