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

    Neuronpedia

    INDEX
    Explanations

    words related to coding and special characters

    oai_token-act-pair · gpt-3.5-turbo

    symbols related to formatting or coding structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Surviv
    -0.79
     fairness
    -0.73
     millenn
    -0.68
     assum
    -0.65
     commissions
    -0.64
     pensions
    -0.64
     surviv
    -0.63
     Mirage
    -0.62
     catering
    -0.60
     Unlimited
    -0.60
    POSITIVE LOGITS
     denotes
    1.22
     suffix
    1.15
    -.
    1.09
     denote
    1.08
     vowel
    1.07
     prefix
    1.05
    É
    1.04
    ï¸ı
    1.04
     signifies
    1.01
    Ïī
    1.00
    Act Density 0.163%

    No Known Activations