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

    Neuronpedia

    INDEX
    Explanations

    words related to standardizing or normalizing processes or entities

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of modification or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thur
    -0.77
    agher
    -0.71
    REL
    -0.71
    backs
    -0.70
    adem
    -0.69
    worldly
    -0.68
    iddles
    -0.67
    stead
    -0.67
    loo
    -0.67
    adra
    -0.65
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢ
    0.74
    SHIP
    0.67
     tendencies
    0.66
    ATION
    0.64
    ATIONS
    0.64
    aign
    0.63
     ACTIONS
    0.63
    ALLY
    0.62
    uration
    0.59
     utilization
    0.59
    Act Density 0.158%

    No Known Activations