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

    Neuronpedia

    INDEX
    Explanations

    phrases related to commenting on or discussing topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comment on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GenerationType
    -0.59
     BIBSYS
    -0.52
    RunWith
    -0.50
     vectorielles
    -0.47
     faſt
    -0.46
    complexContent
    -0.44
     FetchType
    -0.44
    JAKARTA
    -0.40
    Predecesor
    -0.40
     ſind
    -0.40
    POSITIVE LOGITS
     comment
    1.05
     comments
    0.99
     commenting
    0.98
     Comment
    0.94
     COMMENT
    0.94
     COMMENTS
    0.91
    comment
    0.91
    Comment
    0.88
     commentary
    0.88
     commented
    0.88
    Act Density 0.095%

    No Known Activations