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

    Neuronpedia

    INDEX
    Explanations

    words related to reducing something to a particular state or level

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a process of reduction or simplification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ear
    -0.77
    construct
    -0.75
    went
    -0.72
    sett
    -0.72
    uristic
    -0.72
    dominated
    -0.70
    notation
    -0.70
    aram
    -0.70
    gener
    -0.69
    vind
    -0.69
    POSITIVE LOGITS
     earth
    0.70
     basics
    0.69
     Pieces
    0.69
     ashes
    0.68
     brass
    0.67
     scraps
    0.66
    ãĤ©
    0.63
     milliseconds
    0.62
     Basics
    0.62
    osal
    0.62
    Act Density 0.054%

    No Known Activations