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

    Neuronpedia

    INDEX
    Explanations

    words related to insufficiency or inadequacy

    oai_token-act-pair · gpt-3.5-turbo

    expressions of deficiency or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.69
     Circus
    -0.66
     Dug
    -0.65
     Ribbon
    -0.63
     helicop
    -0.61
     Drac
    -0.60
     Grac
    -0.60
    eor
    -0.60
    tnc
    -0.59
     Clim
    -0.59
    POSITIVE LOGITS
    lust
    1.28
    luster
    1.00
    lessly
    0.92
     thereof
    0.90
    igue
    0.75
    abet
    0.74
    ada
    0.73
    enz
    0.73
     negativity
    0.70
    iness
    0.70
    Act Density 0.025%

    No Known Activations