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

    Neuronpedia

    INDEX
    Explanations

    statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    statements of belief or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.69
    worldly
    -0.64
     guiActiveUnfocused
    -0.63
     bearer
    -0.63
    SPONSORED
    -0.62
     Guant
    -0.61
    âĢ¢âĢ¢
    -0.58
    ixt
    -0.58
     Calif
    -0.55
     Osama
    -0.55
    POSITIVE LOGITS
     therefore
    1.22
     furthermore
    1.18
     moreover
    1.05
     however
    1.05
     nevertheless
    0.95
     also
    0.95
     meanwhile
    0.95
    Nevertheless
    0.90
    Nonetheless
    0.90
     nonetheless
    0.89
    Act Density 0.778%

    No Known Activations