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

    Neuronpedia

    INDEX
    Explanations

    names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    names and proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     collide
    -0.75
     disarm
    -0.75
     impact
    -0.74
     humidity
    -0.72
     inclination
    -0.72
     coerc
    -0.72
     biases
    -0.71
     stagger
    -0.71
     preclude
    -0.71
     suspending
    -0.70
    POSITIVE LOGITS
    XXX
    0.87
    XXXX
    0.86
     Kare
    0.85
    RR
    0.79
    xxxx
    0.79
     Doe
    0.78
     Patel
    0.78
    idae
    0.78
     Canaver
    0.74
     Mile
    0.73
    Act Density 0.387%

    No Known Activations