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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positioning or placement

    oai_token-act-pair · gpt-3.5-turbo

    references to existential or philosophical concepts related to positions and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isan
    -0.82
    cest
    -0.74
    chemy
    -0.73
    glers
    -0.70
    ago
    -0.69
    bots
    -0.68
    flows
    -0.68
    pheus
    -0.67
    cules
    -0.66
    ences
    -0.65
    POSITIVE LOGITS
     pedest
    0.87
     disadvantage
    0.78
     detriment
    0.75
     doorstep
    0.70
     sleeve
    0.69
     proverbial
    0.68
    ixel
    0.67
     forefront
    0.67
     unemploy
    0.66
     wrong
    0.66
    Act Density 0.240%

    No Known Activations