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

    Neuronpedia

    INDEX
    Explanations

    relationships and comparisons between entities or subjects

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

    Possessive pronouns after verbs

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.55
    irchen
    -0.51
    ")}
    -0.51
    HideFlags
    -0.48
    WriteLiteral
    -0.45
     réunions
    -0.45
     négociations
    -0.44
     kteří
    -0.44
     camicia
    -0.43
    endaftaran
    -0.43
    POSITIVE LOGITS
     mine
    4.18
     ours
    3.83
     yours
    3.51
    Mine
    3.49
     hers
    3.48
     theirs
    3.47
     Mine
    3.44
    mine
    3.26
     MINE
    3.19
     Ours
    3.03
    Act Density 0.269%

    No Known Activations