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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns in various contexts

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

    pronouns doing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.53
    叶修
    -0.40
     SwitchCompat
    -0.39
    Dış
    -0.39
     snippetHide
    -0.39
    లాలు
    -0.36
    farwydd
    -0.34
    Ligações
    -0.34
     [*]
    -0.33
    httphttps
    -0.32
    POSITIVE LOGITS
     Rip
    0.50
     Kinn
    0.50
     own
    0.50
    Rip
    0.48
    Contenu
    0.47
    ónde
    0.45
    __":
    0.45
     Pelop
    0.45
     CCR
    0.44
    embro
    0.44
    Act Density 0.067%

    No Known Activations