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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ¨
    -0.18
    ji
    -0.16
    asc
    -0.15
     unthinkable
    -0.15
    å¿ħè¦ģ
    -0.14
    entai
    -0.14
    ugh
    -0.14
    asco
    -0.14
    onta
    -0.14
    aber
    -0.14
    POSITIVE LOGITS
     clear
    0.21
     fair
    0.18
     true
    0.18
    true
    0.17
     worth
    0.17
     premature
    0.17
    elight
    0.16
     arg
    0.16
    Clear
    0.16
     perfectly
    0.15
    Act Density 0.100%

    No Known Activations