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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting the suggestion or evaluation of an action

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing the concept of good ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wood
    -0.72
    andise
    -0.70
    anches
    -0.67
    woods
    -0.66
    lighting
    -0.65
    ancers
    -0.65
    stals
    -0.64
     Doors
    -0.62
    oya
    -0.61
    bard
    -0.60
    POSITIVE LOGITS
    ually
    1.03
    terday
    0.69
    ual
    0.69
     HDL
    0.67
    ALLY
    0.67
    Ĥİ
    0.66
     proposition
    0.64
    DEM
    0.64
    orial
    0.63
     accelerator
    0.62
    Act Density 0.019%

    No Known Activations