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

    Neuronpedia

    INDEX
    Explanations

    specific characters or strings made up of special characters

    oai_token-act-pair · gpt-3.5-turbo

    emotional statements or expressions of support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.97
     filtering
    -0.78
     endeav
    -0.77
     slam
    -0.70
     hacking
    -0.69
     bin
    -0.68
     digit
    -0.68
     inverse
    -0.68
     drip
    -0.67
     diluted
    -0.66
    POSITIVE LOGITS
    Newsletter
    1.23
    Said
    1.10
    Contribut
    1.10
    SPONSORED
    1.07
    Refer
    1.04
    Indeed
    1.03
    Thirty
    1.02
    Prof
    1.01
    Asked
    0.98
    Testing
    0.97
    Act Density 0.246%

    No Known Activations