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

    Neuronpedia

    INDEX
    Explanations

    words related to topics or themes being focused on or covered in a discussion, review, or analysis

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to examining topics or issues in depth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     collaborator
    -0.66
     Sabha
    -0.66
    lime
    -0.64
    nown
    -0.64
    Sport
    -0.63
    Jar
    -0.62
    ãĥ¼ãĥ«
    -0.61
     rejoice
    -0.61
    lon
    -0.60
    LI
    -0.59
    POSITIVE LOGITS
     topics
    0.76
     pacing
    0.67
     topical
    0.67
     specifics
    0.65
     how
    0.62
     issues
    0.62
     technical
    0.61
     aspects
    0.61
    Merit
    0.59
    ancy
    0.58
    Act Density 0.207%

    No Known Activations