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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases involving 'less'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a decrease or reduction in something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icion
    -0.72
    ULE
    -0.68
    å¦
    -0.68
    Ds
    -0.66
    pez
    -0.66
     Advis
    -0.64
    raltar
    -0.63
    ovo
    -0.60
    å¯
    -0.60
    ixtures
    -0.59
    POSITIVE LOGITS
    ened
    1.33
    ening
    1.22
     than
    1.22
    ens
    0.93
     intrusive
    0.85
     forgiving
    0.84
     glamorous
    0.84
     risky
    0.84
     invasive
    0.84
     stressful
    0.79
    Act Density 0.053%

    No Known Activations