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

    Neuronpedia

    INDEX
    Explanations

    instances of verbs that indicate existence or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     normalization
    -0.42
    CloseOperation
    -0.42
    awtextra
    -0.41
    reve
    -0.40
    minecraftforge
    -0.38
     tabulation
    -0.38
     tuning
    -0.38
     mott
    -0.37
    scattering
    -0.37
    annotations
    -0.37
    POSITIVE LOGITS
     given
    0.99
     kept
    0.98
     provided
    0.87
     held
    0.83
     accompanied
    0.82
     placed
    0.82
     treated
    0.82
     allowed
    0.82
     removed
    0.82
     handled
    0.82
    Act Density 1.711%

    No Known Activations