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

    Neuronpedia

    INDEX
    Explanations

    phrases related to plans or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing a desire for movement or personal improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.72
    Created
    -0.52
     strikingly
    -0.52
     previous
    -0.51
     inexpl
    -0.49
    ected
    -0.49
     famously
    -0.48
     respectively
    -0.47
     previously
    -0.47
     nearly
    -0.47
    POSITIVE LOGITS
     yourselves
    0.81
     tomorrow
    0.78
     âĢ¦"
    0.75
     someday
    0.69
    !"
    0.65
     wherever
    0.64
     yourself
    0.64
     ASAP
    0.63
     fuckin
    0.63
     ourselves
    0.62
    Act Density 1.180%

    No Known Activations