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

    Neuronpedia

    INDEX
    Explanations

    phrases related to human-made or artificial entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to human-made processes and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alos
    -0.98
    aucus
    -0.91
    esville
    -0.85
    earchers
    -0.82
    achu
    -0.81
    eeks
    -0.80
    irlf
    -0.80
    stadt
    -0.80
    osponsors
    -0.77
    ebus
    -0.76
    POSITIVE LOGITS
     interventions
    0.84
     disasters
    0.81
     disaster
    0.73
     goods
    0.69
     pseudo
    0.69
     versions
    0.68
     excuses
    0.68
     substances
    0.68
     garbage
    0.67
     artificial
    0.67
    Act Density 0.089%

    No Known Activations