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

    Neuronpedia

    INDEX
    Explanations

    mentions of people's opinions and feelings about relationships

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

    don't care what others think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.79
    AndEndTag
    -0.68
    rungsseite
    -0.63
     queſta
    -0.59
    complexContent
    -0.59
    niſſe
    -0.53
     snippetHide
    -0.53
    verwijspagina
    -0.53
    Sklici
    -0.52
     <=",
    -0.51
    POSITIVE LOGITS
     cualquiera
    0.41
    but
    0.38
     valiente
    0.37
    nor
    0.34
    不怕
    0.33
    li
    0.32
    ili
    0.32
    orie
    0.32
    zare
    0.31
     любые
    0.31
    Act Density 0.056%

    No Known Activations