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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions that indicate relationships or connections in sentences

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

    and or nor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pliny
    -0.41
     ब्रेकडाउन
    -0.40
    řen
    -0.39
    rinth
    -0.37
     Loth
    -0.37
    dof
    -0.36
     CanadaChoose
    -0.36
    ToServer
    -0.36
    DockStyle
    -0.36
    pcap
    -0.36
    POSITIVE LOGITS
     Infórmanos
    0.62
     Exacts
    0.52
    InjectAttribute
    0.51
    csolódó
    0.50
    تقاوى
    0.49
     ProtoMessage
    0.49
     ';
    0.47
    انجليز
    0.47
     '.$
    0.46
    uxxxx
    0.46
    Act Density 0.161%

    No Known Activations