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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of straightness or directness

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to straightforwardness or simplicity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.96
     Lauder
    -0.75
    ĸļ
    -0.73
    mble
    -0.73
     livest
    -0.70
     facult
    -0.67
     mur
    -0.66
    7601
    -0.65
     Ples
    -0.64
     confir
    -0.63
    POSITIVE LOGITS
    ened
    1.34
    ening
    1.24
    away
    1.24
    eners
    1.16
    forward
    1.14
    edge
    0.97
    ener
    0.95
    aways
    0.89
    FIX
    0.87
    enstein
    0.85
    Act Density 0.033%

    No Known Activations