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

    Neuronpedia

    INDEX
    Explanations

    phrases or words containing the letters "pot"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "pot" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     silence
    -0.67
     simultane
    -0.67
    IGH
    -0.66
     COR
    -0.62
    ordinary
    -0.57
     obser
    -0.57
     covenant
    -0.56
     planner
    -0.55
     subord
    -0.55
     trib
    -0.55
    POSITIVE LOGITS
    atoes
    1.60
    tery
    1.55
    assium
    1.53
    entially
    1.44
    pour
    1.33
    luck
    1.32
    ential
    1.31
    ato
    1.26
    atos
    1.19
    entials
    1.17
    Act Density 0.031%

    No Known Activations