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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software upgrades and configurations

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and recommendations related to processes or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemThumbnailImage
    -0.78
    argon
    -0.65
    soType
    -0.60
     Emerging
    -0.59
    spoken
    -0.59
    çīĪ
    -0.58
    Poké
    -0.57
     Tales
    -0.57
     Dear
    -0.56
    Welcome
    -0.56
    POSITIVE LOGITS
     removes
    1.20
     eliminates
    1.08
     causes
    1.05
     alters
    1.04
     cancel
    1.02
     reduces
    0.99
     prevents
    0.98
     preserves
    0.96
     ensures
    0.96
     overwrite
    0.96
    Act Density 0.302%

    No Known Activations