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

    Neuronpedia

    INDEX
    Explanations

    words related to basic needs or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to basic needs and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    romeda
    -0.77
    igham
    -0.77
     Tycoon
    -0.74
    isSpecialOrderable
    -0.71
    crow
    -0.67
    ibal
    -0.66
    oping
    -0.64
     Rodrigo
    -0.64
    IDA
    -0.63
    uthor
    -0.63
    POSITIVE LOGITS
     necessities
    1.10
     tenets
    1.07
    basic
    0.93
     arithmetic
    0.90
     principles
    0.87
    lly
    0.87
     outline
    0.84
    tenance
    0.83
    gradient
    0.82
     gist
    0.82
    Act Density 0.028%

    No Known Activations