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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing a quote or piece of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases starting with "Here’s" followed by additional context or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneers
    -0.70
    ibles
    -0.70
    ange
    -0.69
    cair
    -0.68
    hate
    -0.67
     headaches
    -0.63
    esm
    -0.62
    aceutical
    -0.61
    iosity
    -0.61
     extermination
    -0.60
    POSITIVE LOGITS
     hoping
    0.82
     illustrate
    0.71
     excerpt
    0.65
     example
    0.65
     highlights
    0.64
     why
    0.63
     yours
    0.63
     Demo
    0.63
     snippet
    0.62
     courtesy
    0.61
    Act Density 0.056%

    No Known Activations