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

    Neuronpedia

    INDEX
    Explanations

    phrases related to formal requests and organizational communication

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

    Request for information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     niebla
    -0.38
     jagung
    -0.36
     tatuajes
    -0.36
     kasarigan
    -0.36
     bricolaje
    -0.36
     sintética
    -0.35
     gancho
    -0.34
     peligros
    -0.34
     sabiduría
    -0.34
     aliento
    -0.33
    POSITIVE LOGITS
     transférez
    0.53
    PYX
    0.52
    دانشنامهٔ
    0.49
    Framework
    0.45
     pror
    0.45
    pez
    0.44
     project
    0.43
     Project
    0.43
     Esti
    0.43
    rop
    0.43
    Act Density 0.005%

    No Known Activations