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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions for specific actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to providing essential services or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fml
    -0.69
     fare
    -0.67
     ecstasy
    -0.65
     weighing
    -0.62
     litter
    -0.61
    VIDEO
    -0.60
     deem
    -0.59
    category
    -0.58
     behold
    -0.58
     respectively
    -0.58
    POSITIVE LOGITS
    ments
    1.18
    ables
    1.08
    able
    1.04
    acion
    0.96
    ances
    0.93
    ability
    0.91
    ATIONS
    0.90
    ership
    0.89
    ings
    0.88
    ABLE
    0.88
    Act Density 0.143%

    No Known Activations