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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or desire for connection

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

    something or someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oídos
    -0.46
    pgterms
    -0.45
    InjectAttribute
    -0.45
    dafx
    -0.44
     noDo
    -0.43
    itoneum
    -0.43
     Regie
    -0.43
    gorod
    -0.43
     transparence
    -0.42
     transfieras
    -0.41
    POSITIVE LOGITS
    something
    0.70
    someone
    0.70
     something
    0.69
     someone
    0.68
     Someone
    0.63
     Something
    0.63
    Something
    0.62
    Someone
    0.62
     somethin
    0.61
    ETHING
    0.58
    Act Density 0.048%

    No Known Activations