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

    Neuronpedia

    INDEX
    Explanations

    words related to strict and rigid situations or structures

    oai_token-act-pair · gpt-3.5-turbo

    references to economic or ideological constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ULE
    -0.76
    ETF
    -0.74
     WARN
    -0.74
    ERAL
    -0.71
    Interstitial
    -0.70
    ICA
    -0.68
     Werewolf
    -0.67
    IFIC
    -0.66
    MAT
    -0.65
    MT
    -0.65
    POSITIVE LOGITS
     stra
    1.41
     Stra
    1.00
    pping
    0.90
    eties
    0.88
     Strait
    0.87
    pper
    0.86
    fing
    0.85
    cipled
    0.85
     tiss
    0.83
    obar
    0.81
    Act Density 0.004%

    No Known Activations