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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tasks or activities involving effort or physical labor

    oai_token-act-pair · gpt-3.5-turbo

    terms related to work and tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respons
    -0.79
     uncond
    -0.70
     congr
    -0.69
     burnt
    -0.65
     bang
    -0.65
    Reviewer
    -0.62
     dime
    -0.61
     positively
    -0.61
     dstg
    -0.59
     cogn
    -0.58
    POSITIVE LOGITS
    theless
    1.06
    tenance
    0.79
    icity
    0.73
    ments
    0.73
    ment
    0.70
    iculty
    0.70
    recy
    0.70
    Hide
    0.68
    lihood
    0.67
    ionage
    0.67
    Act Density 0.161%

    No Known Activations