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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various types of actions or events

    oai_token-act-pair · gpt-3.5-turbo

    elements related to conflict, social justice, and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Balt
    -0.60
     Tanz
    -0.59
    yip
    -0.57
     Rhod
    -0.53
    Els
    -0.53
    Russ
    -0.51
    Lear
    -0.51
    adobe
    -0.50
    opa
    -0.50
    ipl
    -0.49
    POSITIVE LOGITS
     illustrates
    1.16
     amounted
    1.15
     violates
    1.13
     underscores
    1.10
     seems
    1.10
     deserves
    1.10
     proves
    1.09
     constitutes
    1.08
     seemed
    1.08
     demonstrates
    1.07
    Act Density 1.339%

    No Known Activations